neccam / nslt Goto Github PK
View Code? Open in Web Editor NEWNeural Sign Language Translation (CVPR'18)
License: Apache License 2.0
Neural Sign Language Translation (CVPR'18)
License: Apache License 2.0
After running a code with
python -m nmt --src=sign --tgt=de --train_prefix=../Data/phoenix2014T.train --dev_prefix=../Data/phoenix2014T.dev --test_prefix=../Data/phoenix2014T.test --out_dir=../test_out/ --vocab_prefix=../Data/phoenix2014T.vocab --source_reverse=True --num_units=1000 --num_layers=4 --num_train_steps=150000 --residual=True --attention=luong --base_gpu=0 --unit_type=gru
I was encounter the error shown below
# Job id 0
# Set random seed to 285
# Loading hparams from ../test_out/hparams
saving hparams to ../test_out/hparams
saving hparams to ../test_out/best_bleu/hparams
attention=luong
attention_architecture=standard
base_gpu=0
batch_size=1
beam_width=3
best_bleu=0
best_bleu_dir=../test_out/best_bleu
bpe_delimiter=None
colocate_gradients_with_ops=True
decay_factor=0.98
decay_steps=10000
dev_prefix=../Data/phoenix2014T.dev
dropout=0.2
encoder_type=uni
eos=</s>
epoch_step=0
eval_on_fly=True
forget_bias=1.0
infer_batch_size=32
init_op=glorot_normal
init_weight=0.1
learning_rate=1e-05
length_penalty_weight=0.0
log_device_placement=False
max_gradient_norm=5.0
max_train=0
metrics=[u'bleu']
num_buckets=0
num_embeddings_partitions=0
num_gpus=1
num_layers=4
num_residual_layers=3
num_train_steps=150000
num_units=1000
optimizer=adam
out_dir=../test_out/
pass_hidden_state=True
random_seed=285
residual=True
snapshot_interval=1000
sos=<s>
source_reverse=True
src=sign
src_max_len=300
src_max_len_infer=300
start_decay_step=0
steps_per_external_eval=None
steps_per_stats=100
test_prefix=../Data/phoenix2014T.test
tgt=de
tgt_max_len=50
tgt_max_len_infer=None
tgt_vocab_file=../Data/phoenix2014T.vocab.de
tgt_vocab_size=2891
time_major=True
train_prefix=../Data/phoenix2014T.train
unit_type=gru
vocab_prefix=../Data/phoenix2014T.vocab
# creating train graph ...
num_layers = 4, num_residual_layers=3
cell 0 GRU DropoutWrapper, dropout=0.2 DeviceWrapper, device=/gpu:0
cell 1 GRU DropoutWrapper, dropout=0.2 ResidualWrapper DeviceWrapper, device=/gpu:0
cell 2 GRU DropoutWrapper, dropout=0.2 ResidualWrapper DeviceWrapper, device=/gpu:0
cell 3 GRU DropoutWrapper, dropout=0.2 ResidualWrapper DeviceWrapper, device=/gpu:0
cell 0 GRU DropoutWrapper, dropout=0.2 DeviceWrapper, device=/gpu:0
cell 1 GRU DropoutWrapper, dropout=0.2 ResidualWrapper DeviceWrapper, device=/gpu:0
cell 2 GRU DropoutWrapper, dropout=0.2 ResidualWrapper DeviceWrapper, device=/gpu:0
cell 3 GRU DropoutWrapper, dropout=0.2 ResidualWrapper DeviceWrapper, device=/gpu:0
start_decay_step=0, learning_rate=1e-05, decay_steps 10000, decay_factor 0.98
# Trainable variables
conv1/weights:0, (11, 11, 3, 96), /device:GPU:0
conv1/biases:0, (96,), /device:GPU:0
conv2/weights:0, (5, 5, 48, 256), /device:GPU:0
conv2/biases:0, (256,), /device:GPU:0
conv3/weights:0, (3, 3, 256, 384), /device:GPU:0
conv3/biases:0, (384,), /device:GPU:0
conv4/weights:0, (3, 3, 192, 384), /device:GPU:0
conv4/biases:0, (384,), /device:GPU:0
conv5/weights:0, (3, 3, 192, 256), /device:GPU:0
conv5/biases:0, (256,), /device:GPU:0
fc6/weights:0, (9216, 4096), /device:GPU:0
fc6/biases:0, (4096,), /device:GPU:0
fc7/weights:0, (4096, 4096), /device:GPU:0
fc7/biases:0, (4096,), /device:GPU:0
embeddings/decoder/embedding_decoder:0, (2891, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/gates/kernel:0, (5096, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/candidate/kernel:0, (5096, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/memory_layer/kernel:0, (1000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/gates/kernel:0, (3000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/kernel:0, (3000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/attention_layer/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/output_projection/kernel:0, (1000, 2891), /device:GPU:0
# creating eval graph ...
num_layers = 4, num_residual_layers=3
cell 0 GRU DeviceWrapper, device=/gpu:0
cell 1 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 2 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 3 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 0 GRU DeviceWrapper, device=/gpu:0
cell 1 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 2 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 3 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
start_decay_step=0, learning_rate=1e-05, decay_steps 10000, decay_factor 0.98
# Trainable variables
conv1/weights:0, (11, 11, 3, 96), /device:GPU:0
conv1/biases:0, (96,), /device:GPU:0
conv2/weights:0, (5, 5, 48, 256), /device:GPU:0
conv2/biases:0, (256,), /device:GPU:0
conv3/weights:0, (3, 3, 256, 384), /device:GPU:0
conv3/biases:0, (384,), /device:GPU:0
conv4/weights:0, (3, 3, 192, 384), /device:GPU:0
conv4/biases:0, (384,), /device:GPU:0
conv5/weights:0, (3, 3, 192, 256), /device:GPU:0
conv5/biases:0, (256,), /device:GPU:0
fc6/weights:0, (9216, 4096), /device:GPU:0
fc6/biases:0, (4096,), /device:GPU:0
fc7/weights:0, (4096, 4096), /device:GPU:0
fc7/biases:0, (4096,), /device:GPU:0
embeddings/decoder/embedding_decoder:0, (2891, 1000),
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/gates/kernel:0, (5096, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/candidate/kernel:0, (5096, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/memory_layer/kernel:0, (1000, 1000),
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/gates/kernel:0, (3000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/kernel:0, (3000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/attention_layer/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/output_projection/kernel:0, (1000, 2891), /device:GPU:0
# creating infer graph ...
num_layers = 4, num_residual_layers=3
cell 0 GRU DeviceWrapper, device=/gpu:0
cell 1 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 2 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 3 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 0 GRU DeviceWrapper, device=/gpu:0
cell 1 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 2 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 3 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
start_decay_step=0, learning_rate=1e-05, decay_steps 10000, decay_factor 0.98
# Trainable variables
conv1/weights:0, (11, 11, 3, 96), /device:GPU:0
conv1/biases:0, (96,), /device:GPU:0
conv2/weights:0, (5, 5, 48, 256), /device:GPU:0
conv2/biases:0, (256,), /device:GPU:0
conv3/weights:0, (3, 3, 256, 384), /device:GPU:0
conv3/biases:0, (384,), /device:GPU:0
conv4/weights:0, (3, 3, 192, 384), /device:GPU:0
conv4/biases:0, (384,), /device:GPU:0
conv5/weights:0, (3, 3, 192, 256), /device:GPU:0
conv5/biases:0, (256,), /device:GPU:0
fc6/weights:0, (9216, 4096), /device:GPU:0
fc6/biases:0, (4096,), /device:GPU:0
fc7/weights:0, (4096, 4096), /device:GPU:0
fc7/biases:0, (4096,), /device:GPU:0
embeddings/decoder/embedding_decoder:0, (2891, 1000),
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/gates/kernel:0, (5096, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/candidate/kernel:0, (5096, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/memory_layer/kernel:0, (1000, 1000),
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/gates/kernel:0, (3000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/kernel:0, (3000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/attention_layer/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/output_projection/kernel:0, (1000, 2891),
# log_file=../test_out/log_1557087524
created train model with fresh parameters, time 5.24s
created infer model with fresh parameters, time 0.96s
# 301
src: /home/ubuntu/fullFrame-227x227px/dev/20June_2011_Monday_heute-6514/
ref: und eher wechselhaft geht es mit unserem wetter auch weiter .
nmt: stunden bedeckt bedeckt bedeckt bedeckt bedeckt bedeckt informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren informieren
created eval model with fresh parameters, time 0.76s
eval dev: perplexity 4663.06, time 3785s, Sun May 5 21:22:18 2019.
eval test: perplexity 4627.91, time 4630s, Sun May 5 22:39:29 2019.
created infer model with fresh parameters, time 0.85s
# Start step 0, lr 1e-05, Sun May 5 22:39:30 2019
# Init train iterator, skipping 0 elements
terminate called after throwing an instance of 'std::out_of_range'
what(): basic_string::substr: __pos (which is 140) > this->size() (which is 0)
Could you help me with this please?
Excuse me,I am a newer of this field. About this network architecture, Can I want to use it from English signs to English? or it is only used from German sign language to German spoken language?
Hi!
When I trying to run the training sample,I meet the problem :ValueError: vocab_file does not exist. What's wrong with it? I couldn't find one way to solve it.
@neccam Hi,I also have this problem during training,what wrong with the code ,how can I do?
the problem is:
tensorflow.python.framework.errors_impl.InvalidArgumentError: TypeError: bad argument type for built-in operation
[[Node: PyFunc = PyFunc[Tin=[DT_STRING, DT_BOOL], Tout=[DT_FLOAT], token="pyfunc_5"](arg0, PyFunc/input_1)]]
[[Node: IteratorGetNext = IteratorGetNextoutput_shapes=[[300,227,227,3], [1]], output_types=[DT_FLOAT, DT_INT32], _device="/job:localhost/replica:0/task:0/cpu:0"]]
[[Node: dynamic_seq2seq/decoder/decoder/while/TensorArrayWrite_2/TensorArrayWriteV3/_169 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0
What are the optimal parameters ( number of layers, hidden units ....) to train nslt with glosses as targets ?
@neccam I downloaded (using the dropbox link in the bash file under BestModel) and extracted the files in sign2text.tar.gz and placed them under BestModel/sign2text/
and tried to run nmt.py
with the parameters as specified below.
python -m nmt --out_dir=BestModel/sign2text --inference_input_file=Data/phoenix2014T.test.sign --inference_output_file=model-output --inference_ref_file=Data/phoenix2014T.test.de --base_gpu=0 --vocab_prefix=Data/phoenix2014T.vocab --tgt=de
Error is given by tf.train.latest_checkpoint
in nmt.py
line number 350 as it returns None.
Following it the copy of the error message that I have received.
WARNING:tensorflow:From /mnt/Alice/ISI/Thesis/nslt/nslt/nmt.py:378: The name tf.app.run is deprecated. Please use tf.compat.v1.app.run instead.
WARNING:tensorflow:
The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:
* https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
* https://github.com/tensorflow/addons
* https://github.com/tensorflow/io (for I/O related ops)
If you depend on functionality not listed there, please file an issue.
W0301 17:29:48.804346 139654575957568 lazy_loader.py:50]
The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:
* https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
* https://github.com/tensorflow/addons
* https://github.com/tensorflow/io (for I/O related ops)
If you depend on functionality not listed there, please file an issue.
# Job id 0
# Set random seed to 285
WARNING:tensorflow:From /mnt/Alice/ISI/Thesis/nslt/nslt/nmt.py:334: The name tf.gfile.Exists is deprecated. Please use tf.io.gfile.exists instead.
W0301 17:29:49.116646 139654575957568 module_wrapper.py:139] From /mnt/Alice/ISI/Thesis/nslt/nslt/nmt.py:334: The name tf.gfile.Exists is deprecated. Please use tf.io.gfile.exists instead.
# Loading hparams from BestModel/sign2text/hparams
WARNING:tensorflow:From utils/misc_utils.py:83: The name tf.gfile.GFile is deprecated. Please use tf.io.gfile.GFile instead.
W0301 17:29:49.117575 139654575957568 module_wrapper.py:139] From utils/misc_utils.py:83: The name tf.gfile.GFile is deprecated. Please use tf.io.gfile.GFile instead.
saving hparams to BestModel/sign2text/hparams
saving hparams to BestModel/sign2text/best_bleu/hparams
attention=
attention_architecture=standard
base_gpu=0
batch_size=1
beam_width=3
best_bleu=0
best_bleu_dir=BestModel/sign2text/best_bleu
bpe_delimiter=None
colocate_gradients_with_ops=True
decay_factor=0.98
decay_steps=10000
dev_prefix=None
dropout=0.2
encoder_type=uni
eos=</s>
epoch_step=0
eval_on_fly=True
forget_bias=1.0
infer_batch_size=32
init_op=glorot_normal
init_weight=0.1
learning_rate=1e-05
length_penalty_weight=0.0
log_device_placement=False
max_gradient_norm=5.0
max_train=0
metrics=[u'bleu']
num_buckets=0
num_embeddings_partitions=0
num_gpus=1
num_layers=2
num_residual_layers=0
num_train_steps=10000
num_units=32
optimizer=adam
out_dir=BestModel/sign2text
pass_hidden_state=True
random_seed=285
residual=False
snapshot_interval=1000
sos=<s>
source_reverse=False
src=None
src_max_len=300
src_max_len_infer=300
start_decay_step=0
steps_per_external_eval=None
steps_per_stats=100
test_prefix=None
tgt=de
tgt_max_len=50
tgt_max_len_infer=None
tgt_vocab_file=Data/phoenix2014T.vocab.de
tgt_vocab_size=2891
time_major=True
train_prefix=None
unit_type=lstm
vocab_prefix=Data/phoenix2014T.vocab
WARNING:tensorflow:From inference.py:55: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.
W0301 17:29:49.130767 139654575957568 module_wrapper.py:139] From inference.py:55: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.
WARNING:tensorflow:From /home/lorenzo/anaconda3/envs/nslt/lib/python2.7/site-packages/tensorflow_estimator/python/estimator/api/_v1/estimator/__init__.py:12: The name tf.estimator.inputs is deprecated. Please use tf.compat.v1.estimator.inputs instead.
W0301 17:29:49.143486 139654575957568 module_wrapper.py:139] From /home/lorenzo/anaconda3/envs/nslt/lib/python2.7/site-packages/tensorflow_estimator/python/estimator/api/_v1/estimator/__init__.py:12: The name tf.estimator.inputs is deprecated. Please use tf.compat.v1.estimator.inputs instead.
WARNING:tensorflow:From utils/iterator_utils.py:47: py_func (from tensorflow.python.ops.script_ops) is deprecated and will be removed in a future version.
Instructions for updating:
tf.py_func is deprecated in TF V2. Instead, there are two
options available in V2.
- tf.py_function takes a python function which manipulates tf eager
tensors instead of numpy arrays. It's easy to convert a tf eager tensor to
an ndarray (just call tensor.numpy()) but having access to eager tensors
means `tf.py_function`s can use accelerators such as GPUs as well as
being differentiable using a gradient tape.
- tf.numpy_function maintains the semantics of the deprecated tf.py_func
(it is not differentiable, and manipulates numpy arrays). It drops the
stateful argument making all functions stateful.
W0301 17:29:49.180721 139654575957568 deprecation.py:323] From utils/iterator_utils.py:47: py_func (from tensorflow.python.ops.script_ops) is deprecated and will be removed in a future version.
Instructions for updating:
tf.py_func is deprecated in TF V2. Instead, there are two
options available in V2.
- tf.py_function takes a python function which manipulates tf eager
tensors instead of numpy arrays. It's easy to convert a tf eager tensor to
an ndarray (just call tensor.numpy()) but having access to eager tensors
means `tf.py_function`s can use accelerators such as GPUs as well as
being differentiable using a gradient tape.
- tf.numpy_function maintains the semantics of the deprecated tf.py_func
(it is not differentiable, and manipulates numpy arrays). It drops the
stateful argument making all functions stateful.
WARNING:tensorflow:From utils/iterator_utils.py:57: make_initializable_iterator (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `for ... in dataset:` to iterate over a dataset. If using `tf.estimator`, return the `Dataset` object directly from your input function. As a last resort, you can use `tf.compat.v1.data.make_initializable_iterator(dataset)`.
W0301 17:29:49.321150 139654575957568 deprecation.py:323] From utils/iterator_utils.py:57: make_initializable_iterator (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `for ... in dataset:` to iterate over a dataset. If using `tf.estimator`, return the `Dataset` object directly from your input function. As a last resort, you can use `tf.compat.v1.data.make_initializable_iterator(dataset)`.
WARNING:tensorflow:From alexnet.py:130: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.
W0301 17:29:49.328442 139654575957568 module_wrapper.py:139] From alexnet.py:130: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.
WARNING:tensorflow:From alexnet.py:132: The name tf.get_variable is deprecated. Please use tf.compat.v1.get_variable instead.
W0301 17:29:49.329063 139654575957568 module_wrapper.py:139] From alexnet.py:132: The name tf.get_variable is deprecated. Please use tf.compat.v1.get_variable instead.
WARNING:tensorflow:From alexnet.py:183: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead.
W0301 17:29:49.346043 139654575957568 module_wrapper.py:139] From alexnet.py:183: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead.
WARNING:tensorflow:From alexnet.py:171: The name tf.nn.xw_plus_b is deprecated. Please use tf.compat.v1.nn.xw_plus_b instead.
W0301 17:29:49.431602 139654575957568 module_wrapper.py:139] From alexnet.py:171: The name tf.nn.xw_plus_b is deprecated. Please use tf.compat.v1.nn.xw_plus_b instead.
WARNING:tensorflow:From alexnet.py:192: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.
Instructions for updating:
Please use `rate` instead of `keep_prob`. Rate should be set to `rate = 1 - keep_prob`.
W0301 17:29:49.434792 139654575957568 deprecation.py:506] From alexnet.py:192: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.
Instructions for updating:
Please use `rate` instead of `keep_prob`. Rate should be set to `rate = 1 - keep_prob`.
WARNING:tensorflow:From model.py:77: The name tf.get_variable_scope is deprecated. Please use tf.compat.v1.get_variable_scope instead.
W0301 17:29:49.450800 139654575957568 module_wrapper.py:139] From model.py:77: The name tf.get_variable_scope is deprecated. Please use tf.compat.v1.get_variable_scope instead.
# creating infer graph ...
num_layers = 2, num_residual_layers=0
cell 0 LSTM, forget_bias=1WARNING:tensorflow:From model_helper.py:75: __init__ (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This class is equivalent as tf.keras.layers.LSTMCell, and will be replaced by that in Tensorflow 2.0.
W0301 17:29:49.459327 139654575957568 deprecation.py:323] From model_helper.py:75: __init__ (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This class is equivalent as tf.keras.layers.LSTMCell, and will be replaced by that in Tensorflow 2.0.
DeviceWrapper, device=/gpu:0
cell 1 LSTM, forget_bias=1 DeviceWrapper, device=/gpu:0
WARNING:tensorflow:From model_helper.py:160: __init__ (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This class is equivalent as tf.keras.layers.StackedRNNCells, and will be replaced by that in Tensorflow 2.0.
W0301 17:29:49.461143 139654575957568 deprecation.py:323] From model_helper.py:160: __init__ (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This class is equivalent as tf.keras.layers.StackedRNNCells, and will be replaced by that in Tensorflow 2.0.
WARNING:tensorflow:From model.py:446: dynamic_rnn (from tensorflow.python.ops.rnn) is deprecated and will be removed in a future version.
Instructions for updating:
Please use `keras.layers.RNN(cell)`, which is equivalent to this API
W0301 17:29:49.461896 139654575957568 deprecation.py:323] From model.py:446: dynamic_rnn (from tensorflow.python.ops.rnn) is deprecated and will be removed in a future version.
Instructions for updating:
Please use `keras.layers.RNN(cell)`, which is equivalent to this API
WARNING:tensorflow:From /home/lorenzo/anaconda3/envs/nslt/lib/python2.7/site-packages/tensorflow_core/python/ops/rnn_cell_impl.py:735: add_variable (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
Please use `layer.add_weight` method instead.
W0301 17:29:49.531052 139654575957568 deprecation.py:323] From /home/lorenzo/anaconda3/envs/nslt/lib/python2.7/site-packages/tensorflow_core/python/ops/rnn_cell_impl.py:735: add_variable (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
Please use `layer.add_weight` method instead.
WARNING:tensorflow:From /home/lorenzo/anaconda3/envs/nslt/lib/python2.7/site-packages/tensorflow_core/python/ops/rnn_cell_impl.py:739: calling __init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
W0301 17:29:49.539202 139654575957568 deprecation.py:506] From /home/lorenzo/anaconda3/envs/nslt/lib/python2.7/site-packages/tensorflow_core/python/ops/rnn_cell_impl.py:739: calling __init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
WARNING:tensorflow:From /home/lorenzo/anaconda3/envs/nslt/lib/python2.7/site-packages/tensorflow_core/python/ops/rnn.py:244: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
W0301 17:29:49.575788 139654575957568 deprecation.py:323] From /home/lorenzo/anaconda3/envs/nslt/lib/python2.7/site-packages/tensorflow_core/python/ops/rnn.py:244: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
WARNING:tensorflow:From model.py:277: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.cast` instead.
W0301 17:29:49.610135 139654575957568 deprecation.py:323] From model.py:277: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.cast` instead.
WARNING:tensorflow:From model.py:277: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.cast` instead.
W0301 17:29:49.613713 139654575957568 deprecation.py:323] From model.py:277: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.cast` instead.
cell 0 LSTM, forget_bias=1 DeviceWrapper, device=/gpu:0
cell 1 LSTM, forget_bias=1 DeviceWrapper, device=/gpu:0
WARNING:tensorflow:From /home/lorenzo/anaconda3/envs/nslt/lib/python2.7/site-packages/tensorflow_core/contrib/seq2seq/python/ops/beam_search_decoder.py:971: to_int64 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.cast` instead.
W0301 17:29:49.953177 139654575957568 deprecation.py:323] From /home/lorenzo/anaconda3/envs/nslt/lib/python2.7/site-packages/tensorflow_core/contrib/seq2seq/python/ops/beam_search_decoder.py:971: to_int64 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.cast` instead.
WARNING:tensorflow:From model.py:113: The name tf.trainable_variables is deprecated. Please use tf.compat.v1.trainable_variables instead.
W0301 17:29:50.130557 139654575957568 module_wrapper.py:139] From model.py:113: The name tf.trainable_variables is deprecated. Please use tf.compat.v1.trainable_variables instead.
WARNING:tensorflow:From model.py:149: The name tf.train.Saver is deprecated. Please use tf.compat.v1.train.Saver instead.
W0301 17:29:50.131427 139654575957568 module_wrapper.py:139] From model.py:149: The name tf.train.Saver is deprecated. Please use tf.compat.v1.train.Saver instead.
WARNING:tensorflow:From model.py:149: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.
W0301 17:29:50.131817 139654575957568 module_wrapper.py:139] From model.py:149: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.
start_decay_step=0, learning_rate=1e-05, decay_steps 10000, decay_factor 0.98
# Trainable variables
conv1/weights:0, (11, 11, 3, 96), /device:GPU:0
conv1/biases:0, (96,), /device:GPU:0
conv2/weights:0, (5, 5, 48, 256), /device:GPU:0
conv2/biases:0, (256,), /device:GPU:0
conv3/weights:0, (3, 3, 256, 384), /device:GPU:0
conv3/biases:0, (384,), /device:GPU:0
conv4/weights:0, (3, 3, 192, 384), /device:GPU:0
conv4/biases:0, (384,), /device:GPU:0
conv5/weights:0, (3, 3, 192, 256), /device:GPU:0
conv5/biases:0, (256,), /device:GPU:0
fc6/weights:0, (9216, 4096), /device:GPU:0
fc6/biases:0, (4096,), /device:GPU:0
fc7/weights:0, (4096, 4096), /device:GPU:0
fc7/biases:0, (4096,), /device:GPU:0
embeddings/decoder/embedding_decoder:0, (2891, 32),
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/basic_lstm_cell/kernel:0, (4128, 128), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/basic_lstm_cell/kernel:0, (64, 128), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/decoder/multi_rnn_cell/cell_0/basic_lstm_cell/kernel:0, (64, 128), /device:GPU:0
dynamic_seq2seq/decoder/multi_rnn_cell/cell_0/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/decoder/multi_rnn_cell/cell_1/basic_lstm_cell/kernel:0, (64, 128), /device:GPU:0
dynamic_seq2seq/decoder/multi_rnn_cell/cell_1/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/decoder/output_projection/kernel:0, (32, 2891),
WARNING:tensorflow:From inference.py:137: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.
W0301 17:29:50.161480 139654575957568 module_wrapper.py:139] From inference.py:137: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.
WARNING:tensorflow:From utils/misc_utils.py:134: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.
W0301 17:29:50.161895 139654575957568 module_wrapper.py:139] From utils/misc_utils.py:134: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.
Traceback (most recent call last):
File "/home/lorenzo/anaconda3/envs/nslt/lib/python2.7/runpy.py", line 174, in _run_module_as_main
"__main__", fname, loader, pkg_name)
File "/home/lorenzo/anaconda3/envs/nslt/lib/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/mnt/Alice/ISI/Thesis/nslt/nslt/nmt.py", line 378, in <module>
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/home/lorenzo/anaconda3/envs/nslt/lib/python2.7/site-packages/tensorflow_core/python/platform/app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "/home/lorenzo/anaconda3/envs/nslt/lib/python2.7/site-packages/absl/app.py", line 299, in run
_run_main(main, args)
File "/home/lorenzo/anaconda3/envs/nslt/lib/python2.7/site-packages/absl/app.py", line 250, in _run_main
sys.exit(main(argv))
File "/mnt/Alice/ISI/Thesis/nslt/nslt/nmt.py", line 368, in main
run_main(FLAGS, default_hparams, train_fn, inference_fn)
File "/mnt/Alice/ISI/Thesis/nslt/nslt/nmt.py", line 351, in run_main
inference_fn(ckpt, flags.inference_input_file, trans_file, hparams, num_workers, jobid)
File "inference.py", line 125, in inference
single_worker_inference(infer_model, ckpt, inference_input_file, inference_output_file, hparams)
File "inference.py", line 139, in single_worker_inference
loaded_infer_model = model_helper.load_model(infer_model.model, ckpt, sess, "infer")
File "model_helper.py", line 173, in load_model
model.saver.restore(session, ckpt)
File "/home/lorenzo/anaconda3/envs/nslt/lib/python2.7/site-packages/tensorflow_core/python/training/saver.py", line 1277, in restore
raise ValueError("Can't load save_path when it is None.")
ValueError: Can't load save_path when it is None.
Note : I am working with Cuda 10, tensorflow-gpu==1.15 and I am wanting to perform the inference task only.
Any help would be very much appreciated. I am picking up on tensorflow so I might have missed something very simple, please guide.
Update 2/3/2020 :
After some digging, I found that Checkpoint Guide states that when checkpoints are created, a file called checkpoint
is also creted along with the index, meta and data file, this checkpoint
file is a protocol buffer containing the data for the recent checkpoints and is read by tf.train.get_checkpoint_state
for selecting the latest checkpoint when function tf.train.latest_checkpoint
is called.
Now if author can help us with the missing file then we should be able to run the trained model hopefully.
Please pardon and guide me if I am missing something very obvious.
Hi @neccam , I am confused about the process of the training vocabulary.
Words containing the symbol "__" in training corpus("phoenix2014T.train.gloss") have not appeared in the dev/test gloss corpus. Especially "__ON __", "__OFF__", they are very common in training corpus, but never appear in training corpus. Can I delete it directly?
The size of the vocabulary obtained from training corpus is 1232, but in the paper it is 1066. Is there any preprocessing here?
When i run the inference with the trained model with the evaluation ,the train and the test set i get the following BLEU-4 scores
Train set: 2.0
Dev set: 8.4
Test set: 9.3
How is that possible to get lower scores using the training set?
colocate_gradients_with_ops=True
decay_factor=0.98
decay_steps=10000
dev_prefix=../Data/phoenix2014T.dev
dropout=0.2
encoder_type=uni
eos=
epoch_step=2000
eval_on_fly=True
forget_bias=1.0
infer_batch_size=32
init_op=glorot_normal
init_weight=0.1
learning_rate=1e-05
length_penalty_weight=0.0
log_device_placement=False
max_gradient_norm=5.0
max_train=0
metrics=[u'bleu']
num_buckets=0
num_embeddings_partitions=0
num_gpus=1
num_layers=4
num_residual_layers=3
num_train_steps=150000
num_units=1000
optimizer=adam
out_dir=../test_out_put
pass_hidden_state=True
random_seed=285
residual=True
snapshot_interval=1000
sos=
source_reverse=True
src=sign
src_max_len=300
src_max_len_infer=300
start_decay_step=0
steps_per_external_eval=None
steps_per_stats=100
test_prefix=../Data/phoenix2014T.test
tgt=de
tgt_max_len=50
tgt_max_len_infer=None
tgt_vocab_file=../Data/phoenix2014T.vocab.de
tgt_vocab_size=2891
time_major=True
train_prefix=../Data/phoenix2014T.train
unit_type=gru
vocab_prefix=../Data/phoenix2014T.vocab
num_layers = 4, num_residual_layers=3
cell 0 GRU DropoutWrapper, dropout=0.2 DeviceWrapper, device=/gpu:0
cell 1 GRU DropoutWrapper, dropout=0.2 ResidualWrapper DeviceWrapper, device=/gpu:0
cell 2 GRU DropoutWrapper, dropout=0.2 ResidualWrapper DeviceWrapper, device=/gpu:0
cell 3 GRU DropoutWrapper, dropout=0.2 ResidualWrapper DeviceWrapper, device=/gpu:0
cell 0 GRU DropoutWrapper, dropout=0.2 DeviceWrapper, device=/gpu:0
cell 1 GRU DropoutWrapper, dropout=0.2 ResidualWrapper DeviceWrapper, device=/gpu:0
cell 2 GRU DropoutWrapper, dropout=0.2 ResidualWrapper DeviceWrapper, device=/gpu:0
cell 3 GRU DropoutWrapper, dropout=0.2 ResidualWrapper DeviceWrapper, device=/gpu:0
start_decay_step=0, learning_rate=1e-05, decay_steps 10000, decay_factor 0.98
conv1/weights:0, (11, 11, 3, 96), /device:GPU:0
conv1/biases:0, (96,), /device:GPU:0
conv2/weights:0, (5, 5, 48, 256), /device:GPU:0
conv2/biases:0, (256,), /device:GPU:0
conv3/weights:0, (3, 3, 256, 384), /device:GPU:0
conv3/biases:0, (384,), /device:GPU:0
conv4/weights:0, (3, 3, 192, 384), /device:GPU:0
conv4/biases:0, (384,), /device:GPU:0
conv5/weights:0, (3, 3, 192, 256), /device:GPU:0
conv5/biases:0, (256,), /device:GPU:0
fc6/weights:0, (9216, 4096), /device:GPU:0
fc6/biases:0, (4096,), /device:GPU:0
fc7/weights:0, (4096, 4096), /device:GPU:0
fc7/biases:0, (4096,), /device:GPU:0
embeddings/decoder/embedding_decoder:0, (2891, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/gates/kernel:0, (5096, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/candidate/kernel:0, (5096, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/memory_layer/kernel:0, (1000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/gates/kernel:0, (3000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/kernel:0, (3000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/attention_layer/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/output_projection/kernel:0, (1000, 2891), /device:GPU:0
num_layers = 4, num_residual_layers=3
cell 0 GRU DeviceWrapper, device=/gpu:0
cell 1 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 2 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 3 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 0 GRU DeviceWrapper, device=/gpu:0
cell 1 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 2 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 3 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
start_decay_step=0, learning_rate=1e-05, decay_steps 10000, decay_factor 0.98
conv1/weights:0, (11, 11, 3, 96), /device:GPU:0
conv1/biases:0, (96,), /device:GPU:0
conv2/weights:0, (5, 5, 48, 256), /device:GPU:0
conv2/biases:0, (256,), /device:GPU:0
conv3/weights:0, (3, 3, 256, 384), /device:GPU:0
conv3/biases:0, (384,), /device:GPU:0
conv4/weights:0, (3, 3, 192, 384), /device:GPU:0
conv4/biases:0, (384,), /device:GPU:0
conv5/weights:0, (3, 3, 192, 256), /device:GPU:0
conv5/biases:0, (256,), /device:GPU:0
fc6/weights:0, (9216, 4096), /device:GPU:0
fc6/biases:0, (4096,), /device:GPU:0
fc7/weights:0, (4096, 4096), /device:GPU:0
fc7/biases:0, (4096,), /device:GPU:0
embeddings/decoder/embedding_decoder:0, (2891, 1000),
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/gates/kernel:0, (5096, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/candidate/kernel:0, (5096, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/memory_layer/kernel:0, (1000, 1000),
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/gates/kernel:0, (3000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/kernel:0, (3000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/attention_layer/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/output_projection/kernel:0, (1000, 2891), /device:GPU:0
num_layers = 4, num_residual_layers=3
cell 0 GRU DeviceWrapper, device=/gpu:0
cell 1 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 2 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 3 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 0 GRU DeviceWrapper, device=/gpu:0
cell 1 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 2 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 3 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
start_decay_step=0, learning_rate=1e-05, decay_steps 10000, decay_factor 0.98
conv1/weights:0, (11, 11, 3, 96), /device:GPU:0
conv1/biases:0, (96,), /device:GPU:0
conv2/weights:0, (5, 5, 48, 256), /device:GPU:0
conv2/biases:0, (256,), /device:GPU:0
conv3/weights:0, (3, 3, 256, 384), /device:GPU:0
conv3/biases:0, (384,), /device:GPU:0
conv4/weights:0, (3, 3, 192, 384), /device:GPU:0
conv4/biases:0, (384,), /device:GPU:0
conv5/weights:0, (3, 3, 192, 256), /device:GPU:0
conv5/biases:0, (256,), /device:GPU:0
fc6/weights:0, (9216, 4096), /device:GPU:0
fc6/biases:0, (4096,), /device:GPU:0
fc7/weights:0, (4096, 4096), /device:GPU:0
fc7/biases:0, (4096,), /device:GPU:0
embeddings/decoder/embedding_decoder:0, (2891, 1000),
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/gates/kernel:0, (5096, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/candidate/kernel:0, (5096, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/memory_layer/kernel:0, (1000, 1000),
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/gates/kernel:0, (3000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/kernel:0, (3000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/attention_layer/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/output_projection/kernel:0, (1000, 2891),
loaded train model parameters from ../test_out_put/translate.ckpt-3000, time 0.53s
loaded infer model parameters from ../test_out_put/translate.ckpt-3000, time 0.19s
src: /home/lhb/lihaibo/dataset/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/20June_2011_Monday_heute-6514/
ref: und eher wechselhaft geht es mit unserem wetter auch weiter .
nmt: und abend .
loaded eval model parameters from ../test_out_put/translate.ckpt-3000, time 0.17s
eval dev: perplexity 254.28, time 230s, Thu May 16 16:36:28 2019.
eval test: perplexity 233.68, time 284s, Thu May 16 16:41:12 2019.
loaded infer model parameters from ../test_out_put/translate.ckpt-3000, time 0.14s
decoding to output ../test_out_put/output_dev.
utils/nmt_utils.py:92: UnicodeWarning: Unicode equal comparison failed to convert both arguments to Unicode - interpreting them as being unequal
if tgt_eos and tgt_eos in output:
utils/nmt_utils.py:93: UnicodeWarning: Unicode equal comparison failed to convert both arguments to Unicode - interpreting them as being unequal
output = output[:output.index(tgt_eos)]
done, num sentences 519, time 340s, Thu May 16 16:46:53 2019.
7.37810386603
1.6249558787
0.0
0.0
bleu dev: 0.0
saving hparams to ../test_out_put/hparams
decoding to output ../test_out_put/output_test.
done, num sentences 642, time 410s, Thu May 16 16:53:44 2019.
8.0224883857
1.87303929631
0.0
0.0
bleu test: 0.0
saving hparams to ../test_out_put/hparams
global step 3100 lr 1e-05 step-time 1.48s wps 0.01K ppl 182.79 bleu 0.00
global step 3200 lr 1e-05 step-time 1.47s wps 0.01K ppl 232.43 bleu 0.00
global step 3300 lr 1e-05 step-time 1.46s wps 0.01K ppl 196.97 bleu 0.00
global step 3400 lr 1e-05 step-time 1.46s wps 0.01K ppl 207.05 bleu 0.00
global step 3500 lr 1e-05 step-time 1.46s wps 0.01K ppl 203.68 bleu 0.00
global step 3600 lr 1e-05 step-time 1.45s wps 0.01K ppl 166.05 bleu 0.00
global step 3700 lr 1e-05 step-time 1.46s wps 0.01K ppl 178.25 bleu 0.00
global step 3800 lr 1e-05 step-time 1.46s wps 0.01K ppl 230.54 bleu 0.00
global step 3900 lr 1e-05 step-time 1.46s wps 0.01K ppl 179.09 bleu 0.00
global step 4000 lr 1e-05 step-time 1.46s wps 0.01K ppl 196.14 bleu 0.00
loaded infer model parameters from ../test_out_put/translate.ckpt-4000, time 0.14s
src: /home/lhb/lihaibo/dataset/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/12January_2010_Tuesday_heute-2546/
ref: und diese gefahr bleibt morgen latent im südwesten weil es dort immer wieder mal schneien wird .
nmt: am tag es es es im im im im im .
loaded eval model parameters from ../test_out_put/translate.ckpt-4000, time 0.13s
eval dev: perplexity 179.53, time 231s, Thu May 16 17:22:02 2019.
eval test: perplexity 170.02, time 285s, Thu May 16 17:26:47 2019.
global step 4100 lr 1e-05 step-time 1.46s wps 0.01K ppl 192.79 bleu 0.00
global step 4200 lr 1e-05 step-time 1.46s wps 0.01K ppl 202.87 bleu 0.00
global step 4300 lr 1e-05 step-time 1.46s wps 0.01K ppl 166.21 bleu 0.00
global step 4400 lr 1e-05 step-time 1.46s wps 0.01K ppl 187.75 bleu 0.00
global step 4500 lr 1e-05 step-time 1.46s wps 0.01K ppl 178.40 bleu 0.00
global step 4600 lr 1e-05 step-time 1.46s wps 0.01K ppl 204.50 bleu 0.00
global step 4700 lr 1e-05 step-time 1.46s wps 0.01K ppl 165.70 bleu 0.00
global step 4800 lr 1e-05 step-time 1.46s wps 0.01K ppl 203.29 bleu 0.00
global step 4900 lr 1e-05 step-time 1.45s wps 0.01K ppl 163.18 bleu 0.00
global step 5000 lr 1e-05 step-time 1.45s wps 0.01K ppl 180.28 bleu 0.00
loaded infer model parameters from ../test_out_put/translate.ckpt-5000, time 0.14s
src: /home/lhb/lihaibo/dataset/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/20March_2010_Saturday_heute-7288/
ref: und die werden sich dann morgen weitgehend über die westhälfte ausbreiten .
nmt: am tag ist es .
loaded eval model parameters from ../test_out_put/translate.ckpt-5000, time 0.13s
eval dev: perplexity 178.55, time 232s, Thu May 16 17:54:59 2019.
eval test: perplexity 169.28, time 285s, Thu May 16 17:59:45 2019.
loaded infer model parameters from ../test_out_put/translate.ckpt-5000, time 0.14s
src: /home/lhb/lihaibo/dataset/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/03November_2010_Wednesday_tagesschau-6507/
ref: in der kölner bucht heute nacht milde dreizehn am alpenrand drei grad .
nmt: am tag ist es für .
loaded infer model parameters from ../test_out_put/translate.ckpt-5000, time 0.14s
decoding to output ../test_out_put/output_dev.
done, num sentences 519, time 345s, Thu May 16 18:05:45 2019.
11.9009571822
2.83395047543
0.492454853713
0.0
bleu dev: 0.0
saving hparams to ../test_out_put/hparams
decoding to output ../test_out_put/output_test.
done, num sentences 642, time 416s, Thu May 16 18:12:41 2019.
12.3686181606
2.7527818936
0.58730787531
0.239582596991
bleu test: 0.2
saving hparams to ../test_out_put/hparams
global step 5100 lr 1e-05 step-time 1.46s wps 0.01K ppl 185.91 bleu 0.00
global step 5200 lr 1e-05 step-time 1.46s wps 0.01K ppl 194.11 bleu 0.00
global step 5300 lr 1e-05 step-time 1.46s wps 0.01K ppl 206.56 bleu 0.00
global step 5400 lr 1e-05 step-time 1.46s wps 0.01K ppl 180.96 bleu 0.00
global step 5500 lr 1e-05 step-time 1.45s wps 0.01K ppl 168.81 bleu 0.00
global step 5600 lr 1e-05 step-time 1.46s wps 0.01K ppl 176.96 bleu 0.00
global step 5700 lr 1e-05 step-time 1.46s wps 0.01K ppl 180.14 bleu 0.00
global step 5800 lr 1e-05 step-time 1.46s wps 0.01K ppl 177.76 bleu 0.00
global step 5900 lr 1e-05 step-time 1.46s wps 0.01K ppl 173.97 bleu 0.00
global step 6000 lr 1e-05 step-time 1.46s wps 0.01K ppl 170.78 bleu 0.00
loaded infer model parameters from ../test_out_put/translate.ckpt-6000, time 0.14s
src: /home/lhb/lihaibo/dataset/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/11August_2010_Wednesday_tagesschau-3/
ref: das bedeutet viele wolken und immer wieder zum teil kräftige schauer und gewitter .
nmt: am der es es es es wolken und es .
loaded eval model parameters from ../test_out_put/translate.ckpt-6000, time 0.13s
eval dev: perplexity 168.81, time 232s, Thu May 16 18:40:55 2019.
eval test: perplexity 159.77, time 285s, Thu May 16 18:45:41 2019.
global step 6100 lr 1e-05 step-time 1.46s wps 0.01K ppl 171.46 bleu 0.00
global step 6200 lr 1e-05 step-time 1.46s wps 0.01K ppl 203.31 bleu 0.00
global step 6300 lr 1e-05 step-time 1.45s wps 0.01K ppl 174.52 bleu 0.00
global step 6400 lr 1e-05 step-time 1.45s wps 0.01K ppl 149.63 bleu 0.00
global step 6500 lr 1e-05 step-time 1.46s wps 0.01K ppl 182.97 bleu 0.00
global step 6600 lr 1e-05 step-time 1.46s wps 0.01K ppl 151.10 bleu 0.00
global step 6700 lr 1e-05 step-time 1.45s wps 0.01K ppl 157.83 bleu 0.00
global step 6800 lr 1e-05 step-time 1.46s wps 0.01K ppl 176.99 bleu 0.00
global step 6900 lr 1e-05 step-time 1.46s wps 0.01K ppl 178.05 bleu 0.00
global step 7000 lr 1e-05 step-time 1.46s wps 0.01K ppl 157.36 bleu 0.00
loaded infer model parameters from ../test_out_put/translate.ckpt-7000, time 0.14s
src: /home/lhb/lihaibo/dataset/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/27May_2011_Friday_tagesschau-8122/
ref: morgen sorgt ein ableger des azorenhochs vielerorts für freundliches wetter .
nmt: am der es es morgen morgen den den .
loaded eval model parameters from ../test_out_put/translate.ckpt-7000, time 0.13s
eval dev: perplexity 162.64, time 231s, Thu May 16 19:13:54 2019.
eval test: perplexity 154.09, time 285s, Thu May 16 19:18:39 2019.
loaded infer model parameters from ../test_out_put/translate.ckpt-7000, time 0.14s
src: /home/lhb/lihaibo/dataset/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/02December_2011_Friday_tagesschau-8010/
ref: sonst ist es teilweise klar an den küsten gibt es einzelne schauer .
nmt: am der es es morgen morgen den den .
loaded infer model parameters from ../test_out_put/translate.ckpt-7000, time 0.14s
decoding to output ../test_out_put/output_dev.
done, num sentences 519, time 345s, Thu May 16 19:24:40 2019.
16.3778426893
0.823106867062
0.0
0.0
bleu dev: 0.0
saving hparams to ../test_out_put/hparams
decoding to output ../test_out_put/output_test.
done, num sentences 642, time 417s, Thu May 16 19:31:38 2019.
17.1048890992
1.70820005228
0.0
0.0
bleu test: 0.0
saving hparams to ../test_out_put/hparams
global step 7100 lr 1e-05 step-time 1.46s wps 0.01K ppl 165.73 bleu 0.00
global step 7200 lr 1e-05 step-time 1.46s wps 0.01K ppl 180.19 bleu 0.00
global step 7300 lr 1e-05 step-time 1.46s wps 0.01K ppl 186.95 bleu 0.00
global step 7400 lr 1e-05 step-time 1.46s wps 0.01K ppl 161.96 bleu 0.00
global step 7500 lr 1e-05 step-time 1.45s wps 0.01K ppl 164.82 bleu 0.00
global step 7600 lr 1e-05 step-time 1.46s wps 0.01K ppl 173.30 bleu 0.00
global step 7700 lr 1e-05 step-time 1.46s wps 0.01K ppl 171.22 bleu 0.00
global step 7800 lr 1e-05 step-time 1.45s wps 0.01K ppl 145.10 bleu 0.00
global step 7900 lr 1e-05 step-time 1.46s wps 0.01K ppl 170.34 bleu 0.00
global step 8000 lr 1e-05 step-time 1.46s wps 0.01K ppl 155.19 bleu 0.00
loaded infer model parameters from ../test_out_put/translate.ckpt-8000, time 0.14s
src: /home/lhb/lihaibo/dataset/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/16April_2010_Friday_tagesschau-6577/
ref: das hoch über dem nordatlantik breitet sich ostwärts aus und bestimmt morgen das wetter in weiten teilen deutschlands mit viel sonne und trockener luft .
nmt: am tag die es im im der und und und auch auch auch auch .
loaded eval model parameters from ../test_out_put/translate.ckpt-8000, time 0.13s
eval dev: perplexity 153.14, time 232s, Thu May 16 19:59:52 2019.
eval test: perplexity 147.56, time 285s, Thu May 16 20:04:38 2019.
loaded infer model parameters from ../test_out_put/translate.ckpt-8000, time 0.14s
src: /home/lhb/lihaibo/dataset/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/05April_2011_Tuesday_tagesschau-6420/
ref: sonst setzt sich von südwesten allmählich die sonne durch .
nmt: am nun die es es und den den .
loaded infer model parameters from ../test_out_put/translate.ckpt-8000, time 0.14s
decoding to output ../test_out_put/output_dev.
done, num sentences 519, time 347s, Thu May 16 20:12:20 2019.
20.5708646737
4.74156430021
0.0
0.0
bleu dev: 0.0
saving hparams to ../test_out_put/hparams
decoding to output ../test_out_put/output_test.
done, num sentences 642, time 419s, Thu May 16 20:19:20 2019.
20.536139597
4.74712752732
0.683660044743
0.0
bleu test: 0.0
saving hparams to ../test_out_put/hparams
global step 8100 lr 1e-05 step-time 1.49s wps 0.01K ppl 186.63 bleu 0.00
global step 8200 lr 1e-05 step-time 1.46s wps 0.01K ppl 147.12 bleu 0.00
global step 8300 lr 1e-05 step-time 1.46s wps 0.01K ppl 174.00 bleu 0.00
global step 8400 lr 1e-05 step-time 1.46s wps 0.01K ppl 195.51 bleu 0.00
global step 8500 lr 1e-05 step-time 1.47s wps 0.01K ppl 168.09 bleu 0.00
global step 8600 lr 1e-05 step-time 1.47s wps 0.01K ppl 156.00 bleu 0.00
global step 8700 lr 1e-05 step-time 1.46s wps 0.01K ppl 156.66 bleu 0.00
global step 8800 lr 1e-05 step-time 1.45s wps 0.01K ppl 155.80 bleu 0.00
global step 8900 lr 1e-05 step-time 1.46s wps 0.01K ppl 165.80 bleu 0.00
global step 9000 lr 1e-05 step-time 1.46s wps 0.01K ppl 144.54 bleu 0.00
loaded infer model parameters from ../test_out_put/translate.ckpt-9000, time 0.14s
src: /home/lhb/lihaibo/dataset/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/21November_2009_Saturday_tagesschau-4911/
ref: in der neuen woche unbeständig mit vielen wolken die zeitweise regen bringen .
nmt: am tag die es morgen und den den den regen .
loaded eval model parameters from ../test_out_put/translate.ckpt-9000, time 0.13s
eval dev: perplexity 153.64, time 232s, Thu May 16 20:45:45 2019.
eval test: perplexity 145.05, time 285s, Thu May 16 20:50:31 2019.
loaded infer model parameters from ../test_out_put/translate.ckpt-9000, time 0.14s
src: /home/lhb/lihaibo/dataset/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/21June_2011_Tuesday_tagesschau-1264/
ref: im osten und südosten beginnt der tag noch freundlich während im übrigen land schon schauer und gewitter unterwegs sind .
nmt: am nun die es morgen den den den den regen .
loaded infer model parameters from ../test_out_put/translate.ckpt-9000, time 0.14s
decoding to output ../test_out_put/output_dev.
done, num sentences 519, time 346s, Thu May 16 20:56:33 2019.
17.0109051037
4.73932799638
2.21729209827
0.943421025948
bleu dev: 0.9
saving hparams to ../test_out_put/hparams
decoding to output ../test_out_put/output_test.
done, num sentences 642, time 418s, Thu May 16 21:03:32 2019.
17.3306824749
4.96482052496
2.50959547569
1.26761051914
bleu test: 1.3
saving hparams to ../test_out_put/hparams
global step 9100 lr 1e-05 step-time 1.47s wps 0.01K ppl 155.52 bleu 0.94
global step 9200 lr 1e-05 step-time 1.46s wps 0.01K ppl 159.43 bleu 0.94
global step 9300 lr 1e-05 step-time 1.46s wps 0.01K ppl 169.96 bleu 0.94
global step 9400 lr 1e-05 step-time 1.46s wps 0.01K ppl 152.75 bleu 0.94
global step 9500 lr 1e-05 step-time 1.46s wps 0.01K ppl 153.21 bleu 0.94
global step 9600 lr 1e-05 step-time 1.46s wps 0.01K ppl 134.32 bleu 0.94
global step 9700 lr 1e-05 step-time 1.46s wps 0.01K ppl 168.70 bleu 0.94
global step 9800 lr 1e-05 step-time 1.46s wps 0.01K ppl 149.64 bleu 0.94
global step 9900 lr 1e-05 step-time 1.46s wps 0.01K ppl 162.74 bleu 0.94
global step 10000 lr 1e-05 step-time 1.46s wps 0.01K ppl 139.05 bleu 0.94
loaded infer model parameters from ../test_out_put/translate.ckpt-10000, time 0.14s
src: /home/lhb/lihaibo/dataset/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/09August_2010_Monday_heute-5906/
ref: ihnen einen schönen abend und machen sie es gut .
nmt: im abend .
loaded eval model parameters from ../test_out_put/translate.ckpt-10000, time 0.13s
eval dev: perplexity 140.93, time 232s, Thu May 16 21:31:46 2019.
eval test: perplexity 133.20, time 286s, Thu May 16 21:36:32 2019.
Traceback (most recent call last):
File "/home/lhb/.conda/envs/nsly/lib/python2.7/runpy.py", line 174, in _run_module_as_main
"main", fname, loader, pkg_name)
File "/home/lhb/.conda/envs/nsly/lib/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/home/lhb/lihaibo/code/NSLT/nslt/nslt/nmt.py", line 378, in
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/home/lhb/.conda/envs/nsly/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "/home/lhb/lihaibo/code/NSLT/nslt/nslt/nmt.py", line 368, in main
run_main(FLAGS, default_hparams, train_fn, inference_fn)
File "/home/lhb/lihaibo/code/NSLT/nslt/nslt/nmt.py", line 361, in run_main
train_fn(hparams, target_session=target_session)
File "train.py", line 292, in train
step_result = loaded_train_model.train(train_sess)
File "model.py", line 175, in train
self.batch_size])
File "/home/lhb/.conda/envs/nsly/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 895, in run
run_metadata_ptr)
File "/home/lhb/.conda/envs/nsly/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1124, in _run
feed_dict_tensor, options, run_metadata)
File "/home/lhb/.conda/envs/nsly/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1321, in _do_run
options, run_metadata)
File "/home/lhb/.conda/envs/nsly/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1340, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.UnknownError: exceptions.AttributeError: 'NoneType' object has no attribute 'astype'
[[Node: PyFunc = PyFunc[Tin=[DT_STRING, DT_BOOL], Tout=[DT_FLOAT], token="pyfunc_1"](arg0, PyFunc/input_1)]]
[[Node: IteratorGetNext = IteratorGetNextoutput_shapes=[[300,227,227,3], [1,?], [1,?], [1], [1]], output_types=[DT_FLOAT, DT_INT32, DT_INT32, DT_INT32, DT_INT32], _device="/job:localhost/replica:0/task:0/cpu:0"]]
#12 I follow your solution, however the question still occurs .
Hi,
Thanks for the great work!
Would it please be possible to share a trained model that we can run evaluation on? I do not have the resources to train a model.
Thanks.
Parameter:
python -m nmt --src=gloss --tgt=de --train_prefix=../Data/phoenix2014T.train --dev_prefix=../Data/phoenix2014T.dev --test_prefix=../Data/phoenix2014T.test --out_dir=../OutDir --vocab_prefix=../Data/phoenix2014T.vocab --source_reverse=True --num_units=1000 --num_layers=4 --num_train_steps=150000 --residual=True --attention=luong --base_gpu=0 --unit_type=gru
Error:
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/attention_layer/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/output_projection/kernel:0, (1000, 2891),
created train model with fresh parameters, time 0.83s
created infer model with fresh parameters, time 0.16s
Traceback (most recent call last):
File "/hd/anaconda2/envs/gpu0/lib/python2.7/runpy.py", line 174, in _run_module_as_main
"main", fname, loader, pkg_name)
File "/hd/anaconda2/envs/gpu0/lib/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/ssd/repositorio/nslt-ufam-v2/nslt/nmt.py", line 378, in
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/hd/anaconda2/envs/gpu0/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "/ssd/repositorio/nslt-ufam-v2/nslt/nmt.py", line 368, in main
run_main(FLAGS, default_hparams, train_fn, inference_fn)
File "/ssd/repositorio/nslt-ufam-v2/nslt/nmt.py", line 361, in run_main
train_fn(hparams, target_session=target_session)
File "train.py", line 265, in train
run_full_eval(model_dir, infer_model, infer_sess, eval_model, eval_sess, hparams, summary_writer, sample_src_data, sample_tgt_data)
File "train.py", line 188, in run_full_eval
run_sample_decode(infer_model, infer_sess, model_dir, hparams, summary_writer, sample_src_data, sample_tgt_data)
File "train.py", line 135, in run_sample_decode
_sample_decode(loaded_infer_model, global_step, infer_sess, hparams, infer_model.iterator, src_data, tgt_data, infer_model.src_placeholder, summary_writer)
File "train.py", line 418, in _sample_decode
nmt_outputs, attention_summary = model.decode(sess)
File "model.py", line 409, in decode
_, infer_summary, _, sample_words = self.infer(sess)
File "model.py", line 397, in infer
return sess.run([self.infer_logits, self.infer_summary, self.sample_id, self.sample_words])
File "/hd/anaconda2/envs/gpu0/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 889, in run
run_metadata_ptr)
File "/hd/anaconda2/envs/gpu0/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1120, in _run
feed_dict_tensor, options, run_metadata)
File "/hd/anaconda2/envs/gpu0/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1317, in _do_run
options, run_metadata)
File "/hd/anaconda2/envs/gpu0/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1336, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.UnknownError: exceptions.OSError: [Errno 2] No such file or directory: 'DANN WETTER WECHSELHAFT'
[[Node: PyFunc = PyFuncTin=[DT_STRING], Tout=[DT_INT32], token="pyfunc_4"]]
[[Node: IteratorGetNext = IteratorGetNextoutput_shapes=[[300,227,227,3], [1]], output_types=[DT_FLOAT, DT_INT32], _device="/job:localhost/replica:0/task:0/device:CPU:0"]]
Can you help me?
About this dataset, I want to know how to use the other folders and wether is necessary to re-scale the pictures before training?
@neccam Hi, I still have the same problem as pointed out by @hec44 (even with your change os.environ["CUDA_VISIBLE_DEVICES"] = "0")
tensorflow.python.framework.errors_impl.InvalidArgumentError: TypeError: bad argument type for built-in operation
[[Node: PyFunc = PyFunc[Tin=[DT_STRING, DT_BOOL], Tout=[DT_FLOAT], token="pyfunc_5"](arg0, PyFunc/input_1)]]
[[Node: IteratorGetNext = IteratorGetNextoutput_shapes=[[300,227,227,3], [1]], output_types=[DT_FLOAT, DT_INT32], _device="/job:localhost/replica:0/task:0/cpu:0"]]
[[Node: dynamic_seq2seq/decoder/decoder/while/TensorArrayWrite_1/TensorArrayWriteV3/_189 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_1669_dynamic_seq2seq/decoder/decoder/while/TensorArrayWrite_1/TensorArrayWriteV3", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]]
Here is the command I used:
python -m nmt --src=sign --tgt=de --train_prefix=../Data/phoenix2014T.train --dev_prefix=../Data/phoenix2014T.dev --test_prefix=../Data/phoenix2014T.test --out_dir=../test_out/ --vocab_prefix=../Data/phoenix2014T.vocab --source_reverse=True --num_units=1000 --num_layers=4 --num_train_steps=150000 --residual=True --attention=luong --base_gpu=0 --unit_type=gru --batch_size=1 --num_gpus=1
Would you have any insight on how to solve this problem?
Hi folks,
I meet a problem while using this repo:
In Data/phoenix2014T.test.sign
, I found there was a path named <PATH_TO_EXTRACTED_AND_RESIZED_FRAMES>/features/fullFrame-227x227px/test/28August_2009_Friday_tagesschau-5883/
. But I didn't know how to find fullFrame-227x227px
.
If you could give any ideas, that would be great. Thanks in advance!
I run inference model like that:
python3.7 -m nmt --out_dir=../BestModel/sign2text/ -- inference_input_file=../Data/phoenix2014T.test.sign --inference_output_file=../Data/predictions.de --inference_ref_file=../Data/phoenix2014T.test.de --base_gpu=0
Then i have following error:
nslt/nslt/nmt.py", line 244, in extend_hparams raise ValueError("hparams.vocab_prefix must be provided.") ValueError: hparams.vocab_prefix must be provided.
In arguments i found this line:
parser.add_argument("--vocab_prefix", type=str, default=None, help="""\ Vocab prefix, expect files with src/tgt suffixes.If None, extract from train files.\ """)
Where do i find this vocab_prefix or folder or whatever?
Here is the command I run:
python -m nmt --src=sign --tgt=de --train_prefix=../Data/phoenix2014T.train --dev_prefix=../Data/phoenix2014T.dev --test_prefix=../Data/phoenix2014T.test --out_dir=../test_out/ --vocab_prefix=../Data/phoenix2014T.vocab --source_reverse=True --num_units=1000 --num_layers=4 --num_train_steps=150000 --residual=True --attention=luong --base_gpu=0 --unit_type=gru
Here is the error I get, with python 2.7 and TF 1.3 (or 1.4.1):
# log_file=../test_out/log_1552151343
created train model with fresh parameters, time 0.98s
created infer model with fresh parameters, time 0.23s
# 301
utils/nmt_utils.py:92: UnicodeWarning: Unicode equal comparison failed to convert both arguments to Unicode - interpreting them as being unequal
if tgt_eos and tgt_eos in output:
src: /localHD/phoenix/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/20June_2011_Monday_heute-6514/
ref: und eher wechselhaft geht es mit unserem wetter auch weiter .
nmt: südwind südwind nämlich nämlich nämlich nämlich wochenende wochenende wochenende wochenende wochenende wochenende wochenende wochenende wochenende wochenende wochenende düsseldorf düsseldorf düsseldorf nieselregen nieselregen nieselregen tauwetters tauwetters tauwetters tauwetters tauwetters tauwetters tauwetters tauwetters tauwetters tauwetters tauwetters tauwetters tauwetters tauwetters tauwetters tauwetters tauwetters
created eval model with fresh parameters, time 0.17s
Traceback (most recent call last):
File "/people/belissen/anaconda3/envs/py27_nslt/lib/python2.7/runpy.py", line 174, in _run_module_as_main
"__main__", fname, loader, pkg_name)
File "/people/belissen/anaconda3/envs/py27_nslt/lib/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/people/belissen/Python/nslt-master/nslt/nmt.py", line 378, in <module>
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/people/belissen/anaconda3/envs/py27_nslt/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "/people/belissen/Python/nslt-master/nslt/nmt.py", line 368, in main
run_main(FLAGS, default_hparams, train_fn, inference_fn)
File "/people/belissen/Python/nslt-master/nslt/nmt.py", line 361, in run_main
train_fn(hparams, target_session=target_session)
File "train.py", line 265, in train
run_full_eval(model_dir, infer_model, infer_sess, eval_model, eval_sess, hparams, summary_writer, sample_src_data, sample_tgt_data)
File "train.py", line 189, in run_full_eval
dev_ppl, test_ppl = run_internal_eval(eval_model, eval_sess, model_dir, hparams, summary_writer)
File "train.py", line 148, in run_internal_eval
dev_ppl = _internal_eval(loaded_eval_model, global_step, eval_sess, eval_model.iterator, dev_eval_iterator_feed_dict, summary_writer, "dev")
File "train.py", line 405, in _internal_eval
ppl = model_helper.compute_perplexity(model, sess, label)
File "model_helper.py", line 215, in compute_perplexity
loss, predict_count, batch_size = model.eval(sess)
File "model.py", line 181, in eval
self.batch_size])
File "/people/belissen/anaconda3/envs/py27_nslt/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 889, in run
run_metadata_ptr)
File "/people/belissen/anaconda3/envs/py27_nslt/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1120, in _run
feed_dict_tensor, options, run_metadata)
File "/people/belissen/anaconda3/envs/py27_nslt/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1317, in _do_run
options, run_metadata)
File "/people/belissen/anaconda3/envs/py27_nslt/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1336, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.UnknownError: exceptions.AttributeError: 'NoneType' object has no attribute 'astype'
[[Node: PyFunc = PyFunc[Tin=[DT_STRING, DT_BOOL], Tout=[DT_FLOAT], token="pyfunc_3"](arg0, PyFunc/input_1)]]
[[Node: IteratorGetNext = IteratorGetNext[output_shapes=[[300,227,227,3], [1,?], [1,?], [1], [1]], output_types=[DT_FLOAT, DT_INT32, DT_INT32, DT_INT32, DT_INT32], _device="/job:localhost/replica:0/task:0/device:CPU:0"](Iterator)]]
Hi all,
I am trying to reproduce the result this repo and also newer repo here: https://github.com/neccam/slt
I just wonder how data pre-processed ?
when I download from 1): https://www-i6.informatik.rwth-aachen.de/~koller/RWTH-PHOENIX-2014-T/
and 2): https://www.cihancamgoz.com/files/cvpr2020/
What is the difference between 2 links ?
Thank you so much !!
while training the model using this command:
python -m nmt --src=gloss --tgt=de --train_prefix=../Data/phoenix2014T.train --dev_prefix=../Data/phoenix2014T.dev --test_prefix=../Data/phoenix2014T.test --out_dir=/home/ml2/nslt-master/nslt/model --vocab_prefix=../Data/phoenix2014T.vocab --source_reverse=True --num_units=1000 --num_layers=4 --num_train_steps=150000 --residual=True --attention=luong --base_gpu=0 --unit_type=gru
The error below was raised. Do you know how should I fix it ?
log_file=/home/ml2/nslt-master/nslt/model/log_1616265448
created train model with fresh parameters, time 2.03s
created infer model with fresh parameters, time 0.50s
288
Traceback (most recent call last):
File "/home/ml2/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1327, in _do_call
return fn(*args)
File "/home/ml2/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1306, in _run_fn
status, run_metadata)
File "/usr/lib/python3.6/contextlib.py", line 88, in exit
next(self.gen)
File "/home/ml2/.local/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.UnknownError: SystemError: returned NULL without setting an error
[[Node: PyFunc = PyFunc[Tin=[DT_STRING, DT_BOOL], Tout=[DT_FLOAT], token="pyfunc_5"](arg0, PyFunc/input_1)]]
[[Node: IteratorGetNext = IteratorGetNextoutput_shapes=[[300,227,227,3], [1]], output_types=[DT_FLOAT, DT_INT32], _device="/job:localhost/replica:0/task:0/cpu:0"]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/usr/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/ml2/nslt-master/nslt/nmt.py", line 378, in
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/home/ml2/.local/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "/home/ml2/nslt-master/nslt/nmt.py", line 368, in main
run_main(FLAGS, default_hparams, train_fn, inference_fn)
File "/home/ml2/nslt-master/nslt/nmt.py", line 361, in run_main
train_fn(hparams, target_session=target_session)
File "/home/ml2/nslt-master/nslt/train.py", line 265, in train
run_full_eval(model_dir, infer_model, infer_sess, eval_model, eval_sess, hparams, summary_writer, sample_src_data, sample_tgt_data)
File "/home/ml2/nslt-master/nslt/train.py", line 188, in run_full_eval
run_sample_decode(infer_model, infer_sess, model_dir, hparams, summary_writer, sample_src_data, sample_tgt_data)
File "/home/ml2/nslt-master/nslt/train.py", line 135, in run_sample_decode
_sample_decode(loaded_infer_model, global_step, infer_sess, hparams, infer_model.iterator, src_data, tgt_data, infer_model.src_placeholder, summary_writer)
File "/home/ml2/nslt-master/nslt/train.py", line 418, in _sample_decode
nmt_outputs, attention_summary = model.decode(sess)
File "/home/ml2/nslt-master/nslt/model.py", line 409, in decode
_, infer_summary, _, sample_words = self.infer(sess)
File "/home/ml2/nslt-master/nslt/model.py", line 397, in infer
return sess.run([self.infer_logits, self.infer_summary, self.sample_id, self.sample_words])
File "/home/ml2/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 895, in run
run_metadata_ptr)
File "/home/ml2/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1124, in _run
feed_dict_tensor, options, run_metadata)
File "/home/ml2/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1321, in _do_run
options, run_metadata)
File "/home/ml2/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1340, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.UnknownError: SystemError: returned NULL without setting an error
[[Node: PyFunc = PyFunc[Tin=[DT_STRING, DT_BOOL], Tout=[DT_FLOAT], token="pyfunc_5"](arg0, PyFunc/input_1)]]
[[Node: IteratorGetNext = IteratorGetNextoutput_shapes=[[300,227,227,3], [1]], output_types=[DT_FLOAT, DT_INT32], _device="/job:localhost/replica:0/task:0/cpu:0"]]"
Hi! I don't know where should I put the dataset to train the model.When I try to train the model, there are some errors like that:No such file or directory:b'<PATH_TO_EXTRACTED_AND_RESIZE_FRAMES>/features/fullFame-227x227px/dev/....
And it exists in the function:'get_number_of_frames()'.I have checked the code but still not find the issue.
And I don't know what's the meaning of 'src' and 'tgt' in the train command, and how can I set it.
python -m nmt --src=sign --tgt=de --train_prefix=Data/phoenix2014T.train --dev_prefix=Data/phoenix2014T.dev --test_prefix=Data/phoenix2014T.test --out_dir=<your_output_dir> --vocab_prefix=phoenix2014T.vocab --source_reverse=True --num_units=1000 --num_layers=4 --num_train_steps=150000 --residual=True --attention=luong --base_gpu=<gpu_id> --unit_type=gru
When I try to execute the code always come this error:
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:1
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:1
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:1
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:1
dynamic_seq2seq/decoder/attention/attention_layer/kernel:0, (2000, 1000), /device:GPU:1
dynamic_seq2seq/decoder/output_projection/kernel:0, (1000, 2891),
# log_file=../OutDir/log_1555354553
created train model with fresh parameters, time 1.12s
created infer model with fresh parameters, time 0.51s
# 301
src: /ssd/fullFrame-227x227px/dev/20June_2011_Monday_heute-6514/
ref: und eher wechselhaft geht es mit unserem wetter auch weiter .
Traceback (most recent call last):
File "/hd/anaconda2/envs/tensorflow1.4/lib/python2.7/runpy.py", line 174, in _run_module_as_main
"__main__", fname, loader, pkg_name)
File "/hd/anaconda2/envs/tensorflow1.4/lib/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/ssd/repositorio/nslt-ufam/nslt/nmt.py", line 378, in <module>
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/hd/anaconda2/envs/tensorflow1.4/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "/ssd/repositorio/nslt-ufam/nslt/nmt.py", line 368, in main
run_main(FLAGS, default_hparams, train_fn, inference_fn)
File "/ssd/repositorio/nslt-ufam/nslt/nmt.py", line 361, in run_main
train_fn(hparams, target_session=target_session)
File "train.py", line 265, in train
run_full_eval(model_dir, infer_model, infer_sess, eval_model, eval_sess, hparams, summary_writer, sample_src_data, sample_tgt_data)
File "train.py", line 188, in run_full_eval
run_sample_decode(infer_model, infer_sess, model_dir, hparams, summary_writer, sample_src_data, sample_tgt_data)
File "train.py", line 135, in run_sample_decode
_sample_decode(loaded_infer_model, global_step, infer_sess, hparams, infer_model.iterator, src_data, tgt_data, infer_model.src_placeholder, summary_writer)
File "train.py", line 427, in _sample_decode
utils.print_out(" nmt: %s" % translation)
File "utils/misc_utils.py", line 62, in print_out
print(s, end="", file=sys.stdout)
UnicodeEncodeError: 'ascii' codec can't encode character u'\xe4' in position 11: ordinal not in range(128)
My Anaconda2 configuration
# Name Version Build Channel attrs 19.1.0 pypi_0 pypi backports 1.0 py27_1 backports-abc 0.5 pypi_0 pypi backports-shutil-get-terminal-size 1.0.0 pypi_0 pypi backports-weakref 1.0.post1 pypi_0 pypi backports.weakref 1.0.post1 py27_0 blas 1.0 mkl bleach 1.5.0 pypi_0 pypi ca-certificates 2019.1.23 0 certifi 2019.3.9 py27_0 configparser 3.7.4 pypi_0 pypi decorator 4.4.0 pypi_0 pypi defusedxml 0.5.0 pypi_0 pypi entrypoints 0.3 pypi_0 pypi enum34 1.1.6 pypi_0 pypi funcsigs 1.0.2 pypi_0 pypi functools32 3.2.3.post2 pypi_0 pypi futures 3.2.0 pypi_0 pypi html5lib 0.9999999 pypi_0 pypi intel-openmp 2018.0.0 8 ipaddress 1.0.22 pypi_0 pypi ipykernel 4.10.0 pypi_0 pypi ipython 5.8.0 pypi_0 pypi ipython-genutils 0.2.0 pypi_0 pypi ipywidgets 7.4.2 pypi_0 pypi jinja2 2.10.1 pypi_0 pypi jsonschema 3.0.1 pypi_0 pypi jupyter 1.0.0 pypi_0 pypi jupyter-client 5.2.4 pypi_0 pypi jupyter-console 5.2.0 pypi_0 pypi jupyter-core 4.4.0 pypi_0 pypi libedit 3.1 heed3624_0 libffi 3.2.1 hd88cf55_4 libgcc-ng 7.2.0 hdf63c60_3 libgfortran-ng 7.2.0 hdf63c60_3 libprotobuf 3.5.2 h6f1eeef_0 libstdcxx-ng 7.2.0 hdf63c60_3 markdown 3.1 pypi_0 pypi markupsafe 1.1.1 pypi_0 pypi mistune 0.8.4 pypi_0 pypi mkl 2018.0.2 1 mkl_fft 1.0.1 py27h3010b51_0 mkl_random 1.0.1 py27h629b387_0 mock 2.0.0 pypi_0 pypi nbconvert 5.4.1 pypi_0 pypi nbformat 4.4.0 pypi_0 pypi ncurses 6.0 h9df7e31_2 notebook 5.7.8 pypi_0 pypi numpy 1.14.0 pypi_0 pypi opencv 2.4.11 nppy27_0 menpo openssl 1.0.2p h14c3975_0 pandocfilters 1.4.2 pypi_0 pypi pathlib2 2.3.3 pypi_0 pypi pbr 5.1.3 pypi_0 pypi pexpect 4.7.0 pypi_0 pypi pickleshare 0.7.5 pypi_0 pypi pip 9.0.1 py27_5 prometheus-client 0.6.0 pypi_0 pypi prompt-toolkit 1.0.15 pypi_0 pypi protobuf 3.7.1 pypi_0 pypi ptyprocess 0.6.0 pypi_0 pypi pygments 2.3.1 pypi_0 pypi pyrsistent 0.14.11 pypi_0 pypi python 2.7.14 h1571d57_30 python-dateutil 2.8.0 pypi_0 pypi pyzmq 18.0.1 pypi_0 pypi qtconsole 4.4.3 pypi_0 pypi readline 7.0 ha6073c6_4 scandir 1.10.0 pypi_0 pypi scikit-learn 0.18 pypi_0 pypi scipy 1.0.0 py27hf5f0f52_0 send2trash 1.5.0 pypi_0 pypi setuptools 38.5.0 pypi_0 pypi simplegeneric 0.8.1 pypi_0 pypi singledispatch 3.4.0.3 pypi_0 pypi six 1.12.0 pypi_0 pypi sklearn 0.0 pypi_0 pypi sqlite 3.22.0 h1bed415_0 tensorflow 1.4.0rc1 pypi_0 pypi tensorflow-tensorboard 0.4.0 pypi_0 pypi terminado 0.8.2 pypi_0 pypi testpath 0.4.2 pypi_0 pypi tk 8.6.7 hc745277_3 tornado 5.1.1 pypi_0 pypi traitlets 4.3.2 pypi_0 pypi wcwidth 0.1.7 pypi_0 pypi werkzeug 0.15.2 pypi_0 pypi wheel 0.30.0 pypi_0 pypi widgetsnbextension 3.4.2 pypi_0 pypi zlib 1.2.11 ha838bed_2
I try to download the dataset follow the readme file.
But it turns out "The webpage at ftp://wasserstoff.informatik.rwth-aachen.de/pub/rwth-phoenix/2016/phoenix-2014-T.v3.tar.gz might be temporarily down or it may have moved permanently to a new web address."
Thank you for your contribution!
I just changed the images in the dataset. Put the sign language's picture into openpose to get the skeleton map, and the file name remains the same as the original data set. That is to say, I used the skeleton diagram as the input image. But the shape of the loss curve is very similar, and the difference in numerical value is very small.
I don't think that should happen.Can anyone tell me what this is about.Thank you.
Moreover, the batch size in the hyper parameter setting does not seem to have been used in any Python file. I think this indicates that it is impossible to read the batch size data that I set
hi , after adopting the solution to your #12 problem, the following problems still occur
loaded infer model parameters from ../test_out_put/translate.ckpt-9000, time 0.14s
src: /home/lhb/lihaibo/dataset/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/21November_2009_Saturday_tagesschau-4911/
ref: in der neuen woche unbeständig mit vielen wolken die zeitweise regen bringen .
nmt: am tag die es morgen und den den den regen .
loaded eval model parameters from ../test_out_put/translate.ckpt-9000, time 0.13s
eval dev: perplexity 153.64, time 232s, Thu May 16 20:45:45 2019.
eval test: perplexity 145.05, time 285s, Thu May 16 20:50:31 2019.
loaded infer model parameters from ../test_out_put/translate.ckpt-9000, time 0.14s
src: /home/lhb/lihaibo/dataset/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/21June_2011_Tuesday_tagesschau-1264/
ref: im osten und südosten beginnt der tag noch freundlich während im übrigen land schon schauer und gewitter unterwegs sind .
nmt: am nun die es morgen den den den den regen .
loaded infer model parameters from ../test_out_put/translate.ckpt-9000, time 0.14s
decoding to output ../test_out_put/output_dev.
done, num sentences 519, time 346s, Thu May 16 20:56:33 2019.
17.0109051037
4.73932799638
2.21729209827
0.943421025948
bleu dev: 0.9
saving hparams to ../test_out_put/hparams
decoding to output ../test_out_put/output_test.
done, num sentences 642, time 418s, Thu May 16 21:03:32 2019.
17.3306824749
4.96482052496
2.50959547569
1.26761051914
bleu test: 1.3
saving hparams to ../test_out_put/hparams
global step 9100 lr 1e-05 step-time 1.47s wps 0.01K ppl 155.52 bleu 0.94
global step 9200 lr 1e-05 step-time 1.46s wps 0.01K ppl 159.43 bleu 0.94
global step 9300 lr 1e-05 step-time 1.46s wps 0.01K ppl 169.96 bleu 0.94
global step 9400 lr 1e-05 step-time 1.46s wps 0.01K ppl 152.75 bleu 0.94
global step 9500 lr 1e-05 step-time 1.46s wps 0.01K ppl 153.21 bleu 0.94
global step 9600 lr 1e-05 step-time 1.46s wps 0.01K ppl 134.32 bleu 0.94
global step 9700 lr 1e-05 step-time 1.46s wps 0.01K ppl 168.70 bleu 0.94
global step 9800 lr 1e-05 step-time 1.46s wps 0.01K ppl 149.64 bleu 0.94
global step 9900 lr 1e-05 step-time 1.46s wps 0.01K ppl 162.74 bleu 0.94
global step 10000 lr 1e-05 step-time 1.46s wps 0.01K ppl 139.05 bleu 0.94
loaded infer model parameters from ../test_out_put/translate.ckpt-10000, time 0.14s
src: /home/lhb/lihaibo/dataset/PHOENIX-2014-T-release-v3/PHOENIX-2014-T/features/fullFrame-227x227px/dev/09August_2010_Monday_heute-5906/
ref: ihnen einen schönen abend und machen sie es gut .
nmt: im abend .
loaded eval model parameters from ../test_out_put/translate.ckpt-10000, time 0.13s
eval dev: perplexity 140.93, time 232s, Thu May 16 21:31:46 2019.
eval test: perplexity 133.20, time 286s, Thu May 16 21:36:32 2019.
Traceback (most recent call last):
File "/home/lhb/.conda/envs/nsly/lib/python2.7/runpy.py", line 174, in _run_module_as_main
"main", fname, loader, pkg_name)
File "/home/lhb/.conda/envs/nsly/lib/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/home/lhb/lihaibo/code/NSLT/nslt/nslt/nmt.py", line 378, in
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/home/lhb/.conda/envs/nsly/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "/home/lhb/lihaibo/code/NSLT/nslt/nslt/nmt.py", line 368, in main
run_main(FLAGS, default_hparams, train_fn, inference_fn)
File "/home/lhb/lihaibo/code/NSLT/nslt/nslt/nmt.py", line 361, in run_main
train_fn(hparams, target_session=target_session)
File "train.py", line 292, in train
step_result = loaded_train_model.train(train_sess)
File "model.py", line 175, in train
self.batch_size])
File "/home/lhb/.conda/envs/nsly/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 895, in run
run_metadata_ptr)
File "/home/lhb/.conda/envs/nsly/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1124, in _run
feed_dict_tensor, options, run_metadata)
File "/home/lhb/.conda/envs/nsly/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1321, in _do_run
options, run_metadata)
File "/home/lhb/.conda/envs/nsly/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1340, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.UnknownError: exceptions.AttributeError: 'NoneType' object has no attribute 'astype'
[[Node: PyFunc = PyFunc[Tin=[DT_STRING, DT_BOOL], Tout=[DT_FLOAT], token="pyfunc_1"](arg0, PyFunc/input_1)]]
[[Node: IteratorGetNext = IteratorGetNextoutput_shapes=[[300,227,227,3], [1,?], [1,?], [1], [1]], output_types=[DT_FLOAT, DT_INT32, DT_INT32, DT_INT32, DT_INT32], _device="/job:localhost/replica:0/task:0/cpu:0"]]
Looking forward your reply,thanks !
Hi, utils.misc_utils.check_tensorflow_version()
results in an error if one uses say version 1.15. See the version history here.
def check_tensorflow_version():
if tf.__version__ < "1.2.1":
raise EnvironmentError("Tensorflow version must >= 1.2.1")
The code can be updated to:
def check_tensorflow_version():
def compare_version(version1, version2):
nums1 = version1.split('.')
nums2 = version2.split('.')
n1, n2 = len(nums1), len(nums2)
# compare versions
for i in range(max(n1, n2)):
i1 = int(nums1[i]) if i < n1 else 0
i2 = int(nums2[i]) if i < n2 else 0
if i1 != i2:
return True if i1 > i2 else False
# the versions are equal
return False
if not compare_version(tf.__version__, "1.2.1"):
raise EnvironmentError("Tensorflow version must >= 1.2.1")
How can we generate an attention map image as shown in the paper?
I extracted the images and resized them. Now i try to train the model but it doesnt seem to work. I get "ValueError: vocab_file does not exist."
Any help?
Hi, I'm trying to use the best model which is downloaded from the dropbox link. I'm trying to do inference only without any training.
After downloading and unzipping the files, the issue mentioned in #24 occurs and I added the checkpoint file.
However, I encounter a similar issue in #25 , which suggests that there needs to be hparams file specifying the structure of the best model. Could you please provide that file as well?
The DropBox link to download the file under the BestModel directory is no longer working. @neccam Could you please update the link?
Hello!
In my opinion, the training sample code in your readme is a S2T model, right?
How can I train a S2G2T model in your paper?
conv1/weights:0, (11, 11, 3, 96), /device:GPU:0
conv1/biases:0, (96,), /device:GPU:0
conv2/weights:0, (5, 5, 48, 256), /device:GPU:0
conv2/biases:0, (256,), /device:GPU:0
conv3/weights:0, (3, 3, 256, 384), /device:GPU:0
conv3/biases:0, (384,), /device:GPU:0
conv4/weights:0, (3, 3, 192, 384), /device:GPU:0
conv4/biases:0, (384,), /device:GPU:0
conv5/weights:0, (3, 3, 192, 256), /device:GPU:0
conv5/biases:0, (256,), /device:GPU:0
fc6/weights:0, (9216, 4096), /device:GPU:0
fc6/biases:0, (4096,), /device:GPU:0
fc7/weights:0, (4096, 4096), /device:GPU:0
fc7/biases:0, (4096,), /device:GPU:0
embeddings/decoder/embedding_decoder:0, (2891, 32), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/basic_lstm_cell/kernel:0, (4128, 128), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/basic_lstm_cell/kernel:0, (64, 128), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/decoder/memory_layer/kernel:0, (32, 32), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/basic_lstm_cell/kernel:0, (96, 128), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/basic_lstm_cell/kernel:0, (64, 128), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/decoder/attention/attention_layer/kernel:0, (64, 32), /device:GPU:0
dynamic_seq2seq/decoder/output_projection/kernel:0, (32, 2891), /device:GPU:0
num_layers = 2, num_residual_layers=0
cell 0 LSTM, forget_bias=1 DeviceWrapper, device=/gpu:0
cell 1 LSTM, forget_bias=1 DeviceWrapper, device=/gpu:0
cell 0 LSTM, forget_bias=1 DeviceWrapper, device=/gpu:0
cell 1 LSTM, forget_bias=1 DeviceWrapper, device=/gpu:0
start_decay_step=0, learning_rate=1e-05, decay_steps 10000, decay_factor 0.98
conv1/weights:0, (11, 11, 3, 96), /device:GPU:0
conv1/biases:0, (96,), /device:GPU:0
conv2/weights:0, (5, 5, 48, 256), /device:GPU:0
conv2/biases:0, (256,), /device:GPU:0
conv3/weights:0, (3, 3, 256, 384), /device:GPU:0
conv3/biases:0, (384,), /device:GPU:0
conv4/weights:0, (3, 3, 192, 384), /device:GPU:0
conv4/biases:0, (384,), /device:GPU:0
conv5/weights:0, (3, 3, 192, 256), /device:GPU:0
conv5/biases:0, (256,), /device:GPU:0
fc6/weights:0, (9216, 4096), /device:GPU:0
fc6/biases:0, (4096,), /device:GPU:0
fc7/weights:0, (4096, 4096), /device:GPU:0
fc7/biases:0, (4096,), /device:GPU:0
embeddings/decoder/embedding_decoder:0, (2891, 32),
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/basic_lstm_cell/kernel:0, (4128, 128), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/basic_lstm_cell/kernel:0, (64, 128), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/decoder/memory_layer/kernel:0, (32, 32),
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/basic_lstm_cell/kernel:0, (96, 128), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/basic_lstm_cell/kernel:0, (64, 128), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/decoder/attention/attention_layer/kernel:0, (64, 32), /device:GPU:0
dynamic_seq2seq/decoder/output_projection/kernel:0, (32, 2891), /device:GPU:0
num_layers = 2, num_residual_layers=0
cell 0 LSTM, forget_bias=1 DeviceWrapper, device=/gpu:0
cell 1 LSTM, forget_bias=1 DeviceWrapper, device=/gpu:0
cell 0 LSTM, forget_bias=1 DeviceWrapper, device=/gpu:0
cell 1 LSTM, forget_bias=1 DeviceWrapper, device=/gpu:0
WARNING:tensorflow:From C:\Users\Dell1\Anaconda3\envs\tsf\lib\site-packages\tensorflow\contrib\seq2seq\python\ops\beam_search_decoder.py:985: to_int64 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast
instead.
W1110 22:01:40.660759 21908 deprecation.py:323] From C:\Users\Dell1\Anaconda3\envs\tsf\lib\site-packages\tensorflow\contrib\seq2seq\python\ops\beam_search_decoder.py:985: to_int64 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast
instead.
start_decay_step=0, learning_rate=1e-05, decay_steps 10000, decay_factor 0.98
conv1/weights:0, (11, 11, 3, 96), /device:GPU:0
conv1/biases:0, (96,), /device:GPU:0
conv2/weights:0, (5, 5, 48, 256), /device:GPU:0
conv2/biases:0, (256,), /device:GPU:0
conv3/weights:0, (3, 3, 256, 384), /device:GPU:0
conv3/biases:0, (384,), /device:GPU:0
conv4/weights:0, (3, 3, 192, 384), /device:GPU:0
conv4/biases:0, (384,), /device:GPU:0
conv5/weights:0, (3, 3, 192, 256), /device:GPU:0
conv5/biases:0, (256,), /device:GPU:0
fc6/weights:0, (9216, 4096), /device:GPU:0
fc6/biases:0, (4096,), /device:GPU:0
fc7/weights:0, (4096, 4096), /device:GPU:0
fc7/biases:0, (4096,), /device:GPU:0
embeddings/decoder/embedding_decoder:0, (2891, 32),
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/basic_lstm_cell/kernel:0, (4128, 128), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/basic_lstm_cell/kernel:0, (64, 128), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/decoder/memory_layer/kernel:0, (32, 32),
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/basic_lstm_cell/kernel:0, (96, 128), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/basic_lstm_cell/kernel:0, (64, 128), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/basic_lstm_cell/bias:0, (128,), /device:GPU:0
dynamic_seq2seq/decoder/attention/attention_layer/kernel:0, (64, 32), /device:GPU:0
dynamic_seq2seq/decoder/output_projection/kernel:0, (32, 2891),
WARNING:tensorflow:From D:\BTP\new\nslt\train.py:242: The name tf.gfile.GFile is deprecated. Please use tf.io.gfile.GFile instead.
W1110 22:01:40.832565 21908 deprecation_wrapper.py:119] From D:\BTP\new\nslt\train.py:242: The name tf.gfile.GFile is deprecated. Please use tf.io.gfile.GFile instead.
created train model with fresh parameters, time 1.66s
created infer model with fresh parameters, time 0.33s
b'KUESTE BISSCHEN WOLKE ABER neg-REGEN neg-HABEN'
Traceback (most recent call last):
File "", line 1, in
runfile('D:/BTP/new/nslt/nmt.py', wdir='D:/BTP/new/nslt')
File "C:\Users\Dell1\Anaconda3\envs\tsf\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 827, in runfile
execfile(filename, namespace)
File "C:\Users\Dell1\Anaconda3\envs\tsf\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 110, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)
File "D:/BTP/new/nslt/nmt.py", line 378, in
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "C:\Users\Dell1\Anaconda3\envs\tsf\lib\site-packages\tensorflow\python\platform\app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "C:\Users\Dell1\Anaconda3\envs\tsf\lib\site-packages\absl\app.py", line 299, in run
_run_main(main, args)
File "C:\Users\Dell1\Anaconda3\envs\tsf\lib\site-packages\absl\app.py", line 250, in _run_main
sys.exit(main(argv))
File "D:/BTP/new/nslt/nmt.py", line 368, in main
run_main(FLAGS, default_hparams, train_fn, inference_fn)
File "D:/BTP/new/nslt/nmt.py", line 361, in run_main
train_fn(hparams, target_session=target_session)
File "D:\BTP\new\nslt\train.py", line 265, in train
run_full_eval(model_dir, infer_model, infer_sess, eval_model, eval_sess, hparams, summary_writer, sample_src_data, sample_tgt_data)
File "D:\BTP\new\nslt\train.py", line 188, in run_full_eval
run_sample_decode(infer_model, infer_sess, model_dir, hparams, summary_writer, sample_src_data, sample_tgt_data)
File "D:\BTP\new\nslt\train.py", line 135, in run_sample_decode
_sample_decode(loaded_infer_model, global_step, infer_sess, hparams, infer_model.iterator, src_data, tgt_data, infer_model.src_placeholder, summary_writer)
File "D:\BTP\new\nslt\train.py", line 418, in _sample_decode
nmt_outputs, attention_summary = model.decode(sess)
File "D:\BTP\new\nslt\model.py", line 409, in decode
_, infer_summary, _, sample_words = self.infer(sess)
File "D:\BTP\new\nslt\model.py", line 397, in infer
return sess.run([self.infer_logits, self.infer_summary, self.sample_id, self.sample_words])
File "C:\Users\Dell1\Anaconda3\envs\tsf\lib\site-packages\tensorflow\python\client\session.py", line 950, in run
run_metadata_ptr)
File "C:\Users\Dell1\Anaconda3\envs\tsf\lib\site-packages\tensorflow\python\client\session.py", line 1173, in _run
feed_dict_tensor, options, run_metadata)
File "C:\Users\Dell1\Anaconda3\envs\tsf\lib\site-packages\tensorflow\python\client\session.py", line 1350, in _do_run
run_metadata)
File "C:\Users\Dell1\Anaconda3\envs\tsf\lib\site-packages\tensorflow\python\client\session.py", line 1370, in _do_call
raise type(e)(node_def, op, message)
UnknownError: FileNotFoundError: [WinError 3] The system cannot find the path specified: b'KUESTE BISSCHEN WOLKE ABER neg-REGEN neg-HABEN'
Traceback (most recent call last):
File "C:\Users\Dell1\Anaconda3\envs\tsf\lib\site-packages\tensorflow\python\ops\script_ops.py", line 209, in call
ret = func(*args)
File "D:\BTP\new\nslt\utils\iterator_utils.py", line 73, in get_number_of_frames
return np.int32(len([f for f in listdir(src) if isfile(join(src, f))]))
FileNotFoundError: [WinError 3] The system cannot find the path specified: b'KUESTE BISSCHEN WOLKE ABER neg-REGEN neg-HABEN'
[[{{node PyFunc}}]]
[[IteratorGetNext]]
while printing the "src" we get "b'KUESTE BISSCHEN WOLKE ABER neg-REGEN neg-HABEN'" which I suppose is errenous data.
Can someone help to locate the error.
is it require to use GPU to use this model?
Traceback (most recent call last): File "model/nmt.py", line 378, in <module> tf.app.run(main=main, argv=[sys.argv[0]] + unparsed) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 48, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "model/nmt.py", line 368, in main run_main(FLAGS, default_hparams, train_fn, inference_fn) File "model/nmt.py", line 351, in run_main inference_fn(ckpt, flags.inference_input_file, trans_file, hparams, num_workers, jobid) File "/app/model/inference.py", line 109, in inference single_worker_inference(infer_model, ckpt, inference_input_file, inference_output_file, hparams) File "/app/model/inference.py", line 131, in single_worker_inference nmt_utils.decode_and_evaluate("infer", loaded_infer_model, sess, output_infer, ref_file=None, metrics=hparams.metrics, bpe_delimiter=hparams.bpe_delimiter, beam_width=hparams.beam_width, tgt_eos=hparams.eos) File "/app/model/utils/nmt_utils.py", line 53, in decode_and_evaluate nmt_outputs, _ = model.decode(sess) File "/app/model/model.py", line 397, in decode _, infer_summary, _, sample_words = self.infer(sess) File "/app/model/model.py", line 385, in infer return sess.run([self.infer_logits, self.infer_summary, self.sample_id, self.sample_words]) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 889, in run run_metadata_ptr) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1120, in _run feed_dict_tensor, options, run_metadata) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1317, in _do_run options, run_metadata) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1336, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.UnknownError: exceptions.AttributeError: 'NoneType' object has no attribute 'astype' [[Node: PyFunc = PyFunc[Tin=[DT_STRING, DT_BOOL], Tout=[DT_FLOAT], token="pyfunc_1"](arg0, PyFunc/input_1)]] [[Node: IteratorGetNext = IteratorGetNext[output_shapes=[[300,227,227,3], [1]], output_types=[DT_FLOAT, DT_INT32], _device="/job:localhost/replica:0/task:0/device:CPU:0"](Iterator)]]
I got this problem and also check with another issues. It looks similiar but can't fix
Hi!
I'm trying to run the trainer part, however I'm getting an error, that I don't really understand.
Traceback (most recent call last): File "/home/hec44/myenv/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1327, in _do_call return fn(*args) File "/home/hec44/myenv/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1306, in _run_fn status, run_metadata) File "/usr/lib/python3.6/contextlib.py", line 88, in __exit__ next(self.gen) File "/home/hec44/myenv/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status pywrap_tensorflow.TF_GetCode(status)) tensorflow.python.framework.errors_impl.InvalidArgumentError: TypeError: bad argument type for built-in operation [[Node: PyFunc = PyFunc[Tin=[DT_STRING, DT_BOOL], Tout=[DT_FLOAT], token="pyfunc_5"](arg0, PyFunc/input_1)]] [[Node: IteratorGetNext = IteratorGetNext[output_shapes=[[300,227,227,3], [1]], output_types=[DT_FLOAT, DT_INT32], _device="/job:localhost/replica:0/task:0/cpu:0"](Iterator)]] [[Node: dynamic_seq2seq/decoder/decoder/while/TensorArrayWrite_1/TensorArrayWriteV3/_189 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_1669_dynamic_seq2seq/decoder/decoder/while/TensorArrayWrite_1/TensorArrayWriteV3", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"](^_cloopdynamic_seq2seq/decoder/decoder/while/BeamSearchDecoderStep/decoder/attention/mul/x/_18)]]
This error occurs after creating the training and infer models:
_# log_file=../../outputModel/log_1535347694
created train model with fresh parameters, time 1.58s
created infer model with fresh parameters, time 0.20s_
I only have one GPU.
I've already resized the images and downloades alexnet wieghts
I've got this issue during inference:
~/Desktop/slt/nslt-1/nslt/nslt$ python -m nmt --out_dir=../BestModel/mine --inference_input_file=../Data/phoenix2014T.test.sign --inference_output_file=../BestModel/mine/prediction --inference_ref_file=../Data/phoenix2014T.test.de --vocab_prefix=../Data/phoenix2014T.vocab --base_gpu=0 --tgt=de
saving hparams to ../BestModel/mine/hparams
saving hparams to ../../Out3/best_bleu/hparams
attention=luong
attention_architecture=standard
base_gpu=0
batch_size=1
beam_width=3
best_bleu=0
best_bleu_dir=../../Out3/best_bleu
bpe_delimiter=None
colocate_gradients_with_ops=True
decay_factor=0.98
decay_steps=10000
dev_prefix=../Data/phoenix2014T.dev
dropout=0.2
encoder_type=uni
eos=
epoch_step=4000
eval_on_fly=True
forget_bias=1.0
infer_batch_size=32
init_op=glorot_normal
init_weight=0.1
learning_rate=1e-05
length_penalty_weight=0.0
log_device_placement=False
max_gradient_norm=5.0
max_train=0
metrics=[u'bleu']
num_buckets=0
num_embeddings_partitions=0
num_gpus=1
num_layers=4
num_residual_layers=3
num_train_steps=10000
num_units=1000
optimizer=adam
out_dir=../BestModel/mine
pass_hidden_state=True
random_seed=285
residual=True
snapshot_interval=1000
sos=
source_reverse=True
src=sign
src_max_len=300
src_max_len_infer=300
start_decay_step=0
steps_per_external_eval=None
steps_per_stats=100
test_prefix=None
tgt=de
tgt_max_len=50
tgt_max_len_infer=None
tgt_vocab_file=../Data/phoenix2014T.vocab.de
tgt_vocab_size=2891
time_major=True
train_prefix=../Data/phoenix2014T.train
unit_type=gru
vocab_prefix=../Data/phoenix2014T.vocab
num_layers = 4, num_residual_layers=3
cell 0 GRU DeviceWrapper, device=/gpu:0
cell 1 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 2 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 3 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 0 GRU DeviceWrapper, device=/gpu:0
cell 1 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 2 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
cell 3 GRU ResidualWrapper DeviceWrapper, device=/gpu:0
start_decay_step=0, learning_rate=1e-05, decay_steps 10000, decay_factor 0.98
conv1/weights:0, (11, 11, 3, 96), /device:GPU:0
conv1/biases:0, (96,), /device:GPU:0
conv2/weights:0, (5, 5, 48, 256), /device:GPU:0
conv2/biases:0, (256,), /device:GPU:0
conv3/weights:0, (3, 3, 256, 384), /device:GPU:0
conv3/biases:0, (384,), /device:GPU:0
conv4/weights:0, (3, 3, 192, 384), /device:GPU:0
conv4/biases:0, (384,), /device:GPU:0
conv5/weights:0, (3, 3, 192, 256), /device:GPU:0
conv5/biases:0, (256,), /device:GPU:0
fc6/weights:0, (9216, 4096), /device:GPU:0
fc6/biases:0, (4096,), /device:GPU:0
fc7/weights:0, (4096, 4096), /device:GPU:0
fc7/biases:0, (4096,), /device:GPU:0
embeddings/decoder/embedding_decoder:0, (2891, 1000),
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/gates/kernel:0, (5096, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/candidate/kernel:0, (5096, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_0/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_1/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_2/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/encoder/rnn/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/memory_layer/kernel:0, (1000, 1000),
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/gates/kernel:0, (3000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/kernel:0, (3000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_1/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_2/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:0
dynamic_seq2seq/decoder/attention/attention_layer/kernel:0, (2000, 1000), /device:GPU:0
dynamic_seq2seq/decoder/output_projection/kernel:0, (1000, 2891),
+++++ before model.saver.restore(session, ckpt) +++++ name = infer
Traceback (most recent call last):
File "/usr/lib/python2.7/runpy.py", line 174, in _run_module_as_main
"main", fname, loader, pkg_name)
File "/usr/lib/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/home/mariam/Desktop/slt/nslt-1/nslt/nslt/nmt.py", line 378, in
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "/home/mariam/Desktop/slt/nslt-1/nslt/nslt/nmt.py", line 368, in main
run_main(FLAGS, default_hparams, train_fn, inference_fn)
File "/home/mariam/Desktop/slt/nslt-1/nslt/nslt/nmt.py", line 351, in run_main
inference_fn(ckpt, flags.inference_input_file, trans_file, hparams, num_workers, jobid)
File "inference.py", line 124, in inference
single_worker_inference(infer_model, ckpt, inference_input_file, inference_output_file, hparams)
File "inference.py", line 138, in single_worker_inference
loaded_infer_model = model_helper.load_model(infer_model.model, ckpt, sess, "infer")
File "model_helper.py", line 174, in load_model
model.saver.restore(session, ckpt)
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1560, in restore
{self.saver_def.filename_tensor_name: save_path})
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 895, in run
run_metadata_ptr)
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1124, in _run
feed_dict_tensor, options, run_metadata)
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1321, in _do_run
options, run_metadata)
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1340, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.NotFoundError: Key dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/kernel not found in checkpoint
[[Node: save/RestoreV2_13 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_arg_save/Const_0_0, save/RestoreV2_13/tensor_names, save/RestoreV2_13/shape_and_slices)]]
Caused by op u'save/RestoreV2_13', defined at:
File "/usr/lib/python2.7/runpy.py", line 174, in _run_module_as_main
"main", fname, loader, pkg_name)
File "/usr/lib/python2.7/runpy.py", line 72, in _run_code
exec code in run_globals
File "/home/mariam/Desktop/slt/nslt-1/nslt/nslt/nmt.py", line 378, in
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "/home/mariam/Desktop/slt/nslt-1/nslt/nslt/nmt.py", line 368, in main
run_main(FLAGS, default_hparams, train_fn, inference_fn)
File "/home/mariam/Desktop/slt/nslt-1/nslt/nslt/nmt.py", line 351, in run_main
inference_fn(ckpt, flags.inference_input_file, trans_file, hparams, num_workers, jobid)
File "inference.py", line 121, in inference
infer_model = create_infer_model(model_creator, hparams, scope, single_cell_fn)
File "inference.py", line 60, in create_infer_model
model = model_creator(hparams, iterator=iterator, mode=tf.contrib.learn.ModeKeys.INFER, target_vocab_table=tgt_vocab_table, reverse_target_vocab_table=reverse_tgt_vocab_table, scope=scope, single_cell_fn=single_cell_fn)
File "attention_model.py", line 45, in init
scope=scope, single_cell_fn=single_cell_fn)
File "model.py", line 149, in init
self.saver = tf.train.Saver(tf.global_variables(), save_relative_paths= True)
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1140, in init
self.build()
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1172, in build
filename=self._filename)
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 688, in build
restore_sequentially, reshape)
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 407, in _AddRestoreOps
tensors = self.restore_op(filename_tensor, saveable, preferred_shard)
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 247, in restore_op
[spec.tensor.dtype])[0])
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/ops/gen_io_ops.py", line 663, in restore_v2
dtypes=dtypes, name=name)
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
op_def=op_def)
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2630, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/mariam/venv2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1204, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
NotFoundError (see above for traceback): Key dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/kernel not found in checkpoint
[[Node: save/RestoreV2_13 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_arg_save/Const_0_0, save/RestoreV2_13/tensor_names, save/RestoreV2_13/shape_and_slices)]]
sometimes the issue will change to
Key dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_0/gru_cell/candidate/bias not found in checkpoint
Awesome repo . For our college project i am using this can you share the images after resizing also (like drive link ).
It seems that we no longer have access to the dataset anymore, right? Or it's just temporary maintenance?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.