ronghanghu / cmn Goto Github PK

getting error in 3rd step of the installation

export CMN_ROOT=$(pwd)
cd $CMN_ROOT/util/faster_rcnn_lib/ && make
cd $CMN_ROOT/util/roi_pooling/ && ./compile_roi_pooling.sh
cd $CMN_ROOT

error:

tensorflow/core/util/cuda_kernel_helper.h(52): error: class "Eigen::GpuDevice" has no member "getNumCudaMultiProcessors"

tensorflow/core/util/cuda_kernel_helper.h(52): error: class "Eigen::GpuDevice" has no member "maxCudaThreadsPerMultiProcessor"

tensorflow/core/util/cuda_kernel_helper.h(51): error: no instance of overloaded function "std::min" matches the argument list
            argument types are: (<error-type>, const int)

tensorflow/core/util/cuda_kernel_helper.h(54): error: class "Eigen::GpuDevice" has no member "maxCudaThreadsPerBlock"

tensorflow/core/util/cuda_kernel_helper.h(54): error: no instance of overloaded function "std::min" matches the argument list
            argument types are: (int, <error-type>)

tensorflow/core/util/cuda_kernel_helper.h(57): error: class "Eigen::GpuDevice" has no member "getNumCudaMultiProcessors"

10 errors detected in the compilation of "/tmp/tmpxft_00002353_00000000-7_roi_pooling_op_gpu.cu.cpp1.ii".
g++-4.8: error: roi_pooling_op_gpu.cu.o: No such file or directory

@ronghanghu

I tried to create my own imdb using build_visgeno_imdb.ipynb, but an error occurs.
It says that rel_data of the following lines doesn't exist. Is it relationships?

rel_data_trn = [rel for rel in rel_data if rel['image_id'] in splits['train']]
rel_data_val = [rel for rel in rel_data if rel['image_id'] in splits['val']]
rel_data_tst = [rel for rel in rel_data if rel['image_id'] in splits['test']]

If I change this to relationships, then another error occurs like the following.

Loading ROI data from file...Done.
Exception in thread Thread-1:
Traceback (most recent call last):
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/threading.py", line 916, in _bootstrap_inner
    self.run()
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/threading.py", line 864, in run
    self._target(*self._args, **self._kwargs)
  File "/mnt/brain1/scratch/kylemin/object_detection/cmn/util/visgeno_rel_train/rel_data_reader.py", line 28, in run_prefetch
    vocab_dict, T, max_bbox_num, max_rel_num)
  File "/mnt/brain1/scratch/kylemin/object_detection/cmn/util/visgeno_rel_train/prepare_batch.py", line 12, in load_one_batch
    im_path = iminfo['im_path']
KeyError: 'im_path'

I think that it is needed to save an image path in the build_visgeno_imdb.ipynb file.
Could you look into this error?
Thank you.

Thank you for your code.
For this step "Download the GloVe matrix for word embedding:"
When I run ./word_embedding/download_embed_matrix.sh

got this error:

HTTP request sent, awaiting response... 404 Not Found.

I think the link "http://people.eecs.berkeley.edu/~ronghang/projects/cmn/word_embedding/embed_matrix.tgz" doesn't work for now. Could you share the new link?

Thanks for your helps!

If I try to train the model on Visual Genome, this error occurs.
(tensorflow 1.2.1)

Traceback (most recent call last):
  File "./exp-visgeno-rel/exp_train_visgeno_attbilstm_strong.py", line 65, in 
    text_seq_batch, num_vocab, embed_dim, lstm_dim, vgg_dropout, lstm_dropout)
  File "/mnt/brain1/scratch/kylemin/object_detection/cmn/models/visgeno_attention_model.py", line 23, in visgeno_attbilstm_net
    lstm_dim=lstm_dim, apply_dropout=lstm_dropout)
  File "/mnt/brain1/scratch/kylemin/object_detection/cmn/models/lstm_net.py", line 46, in attbilstm
    scope="bidirectional_lstm2")
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 375, in bidirectional_dynamic_rnn
    time_major=time_major, scope=fw_scope)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 574, in dynamic_rnn
    dtype=dtype)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 737, in _dynamic_rnn_loop
    swap_memory=swap_memory)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2770, in while_loop
    result = context.BuildLoop(cond, body, loop_vars, shape_invariants)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2599, in BuildLoop
    pred, body, original_loop_vars, loop_vars, shape_invariants)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2549, in _BuildLoop
    body_result = body(*packed_vars_for_body)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 720, in _time_step
    skip_conditionals=True)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 206, in _rnn_step
    new_output, new_state = call_cell()
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 708, in 
    call_cell = lambda: cell(input_t, state)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/rnn_cell_impl.py", line 180, in __call__
    return super(RNNCell, self).__call__(inputs, state)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/layers/base.py", line 441, in __call__
    outputs = self.call(inputs, *args, **kwargs)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/rnn_cell_impl.py", line 383, in call
    concat = _linear([inputs, h], 4 * self._num_units, True)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/rnn_cell_impl.py", line 1017, in _linear
    initializer=kernel_initializer)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 1065, in get_variable
    use_resource=use_resource, custom_getter=custom_getter)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 962, in get_variable
    use_resource=use_resource, custom_getter=custom_getter)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 360, in get_variable
    validate_shape=validate_shape, use_resource=use_resource)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/rnn_cell_impl.py", line 183, in _rnn_get_variable
    variable = getter(*args, **kwargs)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 352, in _true_getter
    use_resource=use_resource)
  File "/mnt/brain1/scratch/kylemin/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 669, in _get_single_variable
    found_var.get_shape()))
ValueError: Trying to share variable lstm/bidirectional_lstm1/fw/basic_lstm_cell/kernel, but specified shape (3000, 4000) and found shape (1300, 4000).

Thank you.

Hi,
it would be very nice if you could provide pretrained models for the Visual Genome and Google-Ref datasets. Is this possible?
Cheers,
Oier

I'm trying to build the ROIPolling operation with TF 1.15.0, CUDA 10.2 and g++-7.5.0, but I'm getting the following errors:

`/lib/python3.6/site-packages/tensorflow_core/include/absl/strings/string_view.h(495): error: constexpr function return is non-constant

tensorflow/core/util/cuda_kernel_helper.h(52): error: class "Eigen::GpuDevice" has no member "getNumCudaMultiProcessors"

tensorflow/core/util/cuda_kernel_helper.h(52): error: class "Eigen::GpuDevice" has no member "maxCudaThreadsPerMultiProcessor"

tensorflow/core/util/cuda_kernel_helper.h(51): error: no instance of overloaded function "std::min" matches the argument list
argument types are: (, const int)

tensorflow/core/util/cuda_kernel_helper.h(54): error: class "Eigen::GpuDevice" has no member "maxCudaThreadsPerBlock"

tensorflow/core/util/cuda_kernel_helper.h(54): error: no instance of overloaded function "std::min" matches the argument list
argument types are: (int, )

tensorflow/core/util/cuda_kernel_helper.h(57): error: class "Eigen::GpuDevice" has no member "getNumCudaMultiProcessors"`

I was wondering if these sound familiar to anyone. Thanks!

In the folder cmn/exp-cub200/data/ how did you get train_bboxes.json,test_bboxes.json and val_bboxes.json? Which are being used in the

build_cub200_imdb.ipynb?

Hi,
When I run the file build_visgeno_imdb.ipynb, the result shows 'rel_data' is not defined. Could you give me some help about this problem?