keisks / robsut-wrod-reocginiton Goto Github PK

Traceback (most recent call last):
File "predict.py", line 135, in <module>
  model = load_model(model_file)
File "C:\Python35\lib\site-packages\keras\models.py", line 280, in load_model
  model.optimizer.set_weights(optimizer_weight_values)
File "C:\Python35\lib\site-packages\keras\optimizers.py", line 79, in set_weights
  'provided weight shape ' + str(w.shape))
ValueError: Optimizer weight shape (2600,) not compatible with provided weight shape (650, 10002)

.conda/envs/py27/lib/python2.7/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters
Using TensorFlow backend.
===== EXP SETTING =====
num epoch:	30
num units:	650
batch size:	20
noise type:	JUMBLE
jumble type:	INT
is pilot?:	False
===== LOADING VOCAB =====
#vocab:	 10000
#tokens in training:	 990180
#tokens in validation:	 41821
===== VECTORIZING DATA =====
99 % for train data
99 % for dev data
data shape (#_batches, batch_size, vector_size)
X_train (49509, 20, 228)
Y_train (49509, 20, 10002)
X_dev (2091, 20, 228)
Y_dev (2091, 20, 10002)
Traceback (most recent call last):
  File "train.py", line 182, in <module>
    result_file = open('./results/' + EXP_NAME +'.result', 'w')
IOError: [Errno 2] No such file or directory: './results/train_j-INT_n-JUMBLE_u-650_batch-20.result'