InvalidArgumentError during test

[michelecafagna26]

full stack trace:

Caused by op u'save/Assign_42', defined at: File "style_transfer.py", line 232, in model = create_model(sess, args, vocab) File "style_transfer.py", line 196, in create_model model = Model(args, vocab) File "style_transfer.py", line 159, in init self.saver = tf.train.Saver() File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1140, in init self.build() File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1172, in build filename=self._filename) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 688, in build restore_sequentially, reshape) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 419, in _AddRestoreOps assign_ops.append(saveable.restore(tensors, shapes)) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 155, in restore self.op.get_shape().is_fully_defined()) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/state_ops.py", line 274, in assign validate_shape=validate_shape) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_state_ops.py", line 43, in assign use_locking=use_locking, name=name) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op op_def=op_def) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2630, in create_op original_op=self._default_original_op, op_def=op_def) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1204, in init self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [128] rhs shape= [32] [[Node: save/Assign_42 = Assign[T=DT_FLOAT, _class=["loc:@discriminator1/conv-maxpool-1/b"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/gpu:0"](discriminator1/conv-maxpool-1/b/Adam, save/RestoreV2_42/_43)]]

Using: -nvidia-docker , with official docker image tensorflow/tensorflow:1.3.0-gpu -python 2.7.12 -tensorflow 1.3.0

with this training configuration

{ 'batch_size': 8, 'beam': 1, 'dev': '../data/datadev', 'dim_emb': 100, 'dim_y': 100, 'dim_z': 100, 'dropout_keep_prob': 0.5, 'embedding': '', 'filter_sizes': '1,2,3,4,5', 'gamma_decay': 1, 'gamma_init': 0.1, 'gamma_min': 0.1, 'learning_rate': 0.0005, 'load_model': False, 'max_epochs': 20, 'max_seq_length': 20, 'max_train_size': -1, 'model': '../model/model', 'n_filters': 32, 'n_layers': 1, 'online_testing': False, 'output': '../out/data.dev', 'rho': 1, 'steps_per_checkpoint': 1000, 'test': '', 'train': '../data/data.train', 'vocab': '../out/data.vocab'}