Skip to content
This repository has been archived by the owner on Dec 29, 2022. It is now read-only.

InvalidArgumentError in evaluation #102

Closed
rihardsk opened this issue Mar 23, 2017 · 1 comment
Closed

InvalidArgumentError in evaluation #102

rihardsk opened this issue Mar 23, 2017 · 1 comment

Comments

@rihardsk
Copy link

I am trying to run the nmt_large.yml experiment with my own data. I have also included train_seq2seq.yml and text_metrics_bpe.yml. Basically everything is according to the NMT tutorial.

When training gets to evaluation, it crashes with:

InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 6553600 values, but the requested shape has 0
         [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]]
         [[Node: mean/broadcast_weights/assert_broadcastable/AssertGuard/Assert/Switch_2/_429 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_426_mean/broadcast_weights/assert_broadcastable/AssertGuard/Assert/Switch_2", tensor_type=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

Here's the full stack trace and some logs before that:

INFO:tensorflow:global_step/sec: 1.41102
INFO:tensorflow:loss = 6.79511, step = 901 (70.871 sec)
INFO:tensorflow:tokens/sec: 8544.36
INFO:tensorflow:Creating AttentionSeq2Seq in mode=eval
INFO:tensorflow:
AttentionSeq2Seq:
  !!python/unicode 'attention.class': !!python/unicode 'seq2seq.decoders.attention.AttentionLayerBahdanau'
  !!python/unicode 'attention.params': {num_units: 512}
  !!python/unicode 'bridge.class': !!python/unicode 'seq2seq.models.bridges.ZeroBridge'
  !!python/unicode 'bridge.params': {}
  !!python/unicode 'decoder.class': !!python/unicode 'seq2seq.decoders.AttentionDecoder'
  !!python/unicode 'decoder.params':
    rnn_cell:
      cell_class: LSTMCell
      cell_params: {num_units: 512}
      dropout_input_keep_prob: 0.8
      dropout_output_keep_prob: 1.0
      num_layers: 4
  !!python/unicode 'embedding.dim': 512
  !!python/unicode 'embedding.share': false
  !!python/unicode 'encoder.class': !!python/unicode 'seq2seq.encoders.BidirectionalRNNEncoder'
  !!python/unicode 'encoder.params':
    rnn_cell:
      cell_class: LSTMCell
      cell_params: {num_units: 512}
      dropout_input_keep_prob: 0.8
      dropout_output_keep_prob: 1.0
      num_layers: 2
  !!python/unicode 'inference.beam_search.beam_width': 0
  !!python/unicode 'inference.beam_search.choose_successors_fn': !!python/unicode 'choose_top_k'
  !!python/unicode 'inference.beam_search.length_penalty_weight': 0.0
  !!python/unicode 'optimizer.clip_gradients': 5.0
  !!python/unicode 'optimizer.learning_rate': 0.0001
  !!python/unicode 'optimizer.lr_decay_rate': 0.99
  !!python/unicode 'optimizer.lr_decay_steps': 100
  !!python/unicode 'optimizer.lr_decay_type': !!python/unicode ''
  !!python/unicode 'optimizer.lr_min_learning_rate': 1.0e-12
  !!python/unicode 'optimizer.lr_staircase': false
  !!python/unicode 'optimizer.lr_start_decay_at': 0
  !!python/unicode 'optimizer.lr_stop_decay_at': 1000000000.0
  !!python/unicode 'optimizer.name': !!python/unicode 'Adam'
  !!python/unicode 'source.max_seq_len': 50
  !!python/unicode 'source.reverse': false
  !!python/unicode 'target.max_seq_len': 50
  !!python/unicode 'vocab_source': !!python/unicode '/home/rihards/experiments/seq2seq/en-lv-constrained-baseline-simple-tc/scripts/../data/general.vocab.bpe.32000'
  !!python/unicode 'vocab_target': !!python/unicode '/home/rihards/experiments/seq2seq/en-lv-constrained-baseline-simple-tc/scripts/../data/general.vocab.bpe.32000'

INFO:tensorflow:Creating vocabulary lookup table of size 32601
INFO:tensorflow:Creating vocabulary lookup table of size 32601
INFO:tensorflow:Creating BidirectionalRNNEncoder in mode=eval
INFO:tensorflow:
BidirectionalRNNEncoder:
  rnn_cell:
    cell_class: LSTMCell
    cell_params: {num_units: 512}
    dropout_input_keep_prob: 0.8
    dropout_output_keep_prob: 1.0
    num_layers: 2
    residual_combiner: add
    residual_connections: false
    residual_dense: false

INFO:tensorflow:Creating AttentionLayerBahdanau in mode=eval
INFO:tensorflow:
AttentionLayerBahdanau: {!!python/unicode 'num_units': 512}

INFO:tensorflow:Creating AttentionDecoder in mode=eval
INFO:tensorflow:
AttentionDecoder:
  !!python/unicode 'max_decode_length': 100
  !!python/unicode 'rnn_cell':
    cell_class: LSTMCell
    cell_params: {num_units: 512}
    dropout_input_keep_prob: 0.8
    dropout_output_keep_prob: 1.0
    num_layers: 4
    residual_combiner: add
    residual_connections: false
    residual_dense: false

INFO:tensorflow:Creating ZeroBridge in mode=eval
INFO:tensorflow:
ZeroBridge: {}

INFO:tensorflow:Starting evaluation at 2017-03-23-10:29:43
2017-03-23 12:29:43.447963: I tensorflow/core/common_runtime/gpu/gpu_device.cc:977] Creating TensorFlow device (/gpu:0) -> (device: 0, name: TITAN X (Pascal), pci bus id: 0000:02:00.0)
INFO:tensorflow:Restoring parameters from /home/rihards/experiments/seq2seq/en-lv-constrained-baseline-simple-tc/scripts/../model/model.ckpt-900
2017-03-23 12:29:43.911377: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 6553600 values, but the requested shape has 0
         [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]]
2017-03-23 12:29:43.912289: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Input to reshape is a tensor with 6553600 values, but the requested shape has 0
         [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]]
Traceback (most recent call last):
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/runpy.py", line 174, in _run_module_as_main
    "__main__", fname, loader, pkg_name)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/runpy.py", line 72, in _run_code
    exec code in run_globals
  File "/home/rihards/programming/seq2seq/bin/train.py", line 263, in <module>
    tf.app.run()
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "/home/rihards/programming/seq2seq/bin/train.py", line 258, in main
    schedule=FLAGS.schedule)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/learn_runner.py", line 111, in run
    return _execute_schedule(experiment, schedule)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/learn_runner.py", line 46, in _execute_schedule
    return task()
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/experiment.py", line 440, in train_and_evaluate
    self.train(delay_secs=0)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/experiment.py", line 230, in train
    monitors=self._train_monitors + extra_hooks)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/util/deprecation.py", line 281, in new_func
    return func(*args, **kwargs)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 430, in fit
    loss = self._train_model(input_fn=input_fn, hooks=hooks)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 981, in _train_model
    _, loss = mon_sess.run([model_fn_ops.train_op, model_fn_ops.loss])
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 484, in run
    run_metadata=run_metadata)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 821, in run
    run_metadata=run_metadata)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 777, in run
    return self._sess.run(*args, **kwargs)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 939, in run
    run_metadata=run_metadata))
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/monitors.py", line 1155, in after_run
    induce_stop = m.step_end(self._last_step, result)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/monitors.py", line 356, in step_end
    return self.every_n_step_end(step, output)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/monitors.py", line 662, in every_n_step_end
    name=self.name)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/util/deprecation.py", line 281, in new_func
    return func(*args, **kwargs)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 518, in evaluate
    log_progress=log_progress)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 830, in _evaluate_model
    config=config_pb2.ConfigProto(allow_soft_placement=True))
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/training/evaluation.py", line 182, in _evaluate_once
    session.run(eval_ops, feed_dict)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 484, in run
    run_metadata=run_metadata)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 821, in run
    run_metadata=run_metadata)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 777, in run
    return self._sess.run(*args, **kwargs)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 931, in run
    run_metadata=run_metadata)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 777, in run
    return self._sess.run(*args, **kwargs)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 786, in run
    run_metadata_ptr)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 994, in _run
    feed_dict_string, options, run_metadata)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1044, in _do_run
    target_list, options, run_metadata)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1064, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 6553600 values, but the requested shape has 0
         [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]]
         [[Node: mean/broadcast_weights/assert_broadcastable/AssertGuard/Assert/Switch_2/_429 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_426_mean/broadcast_weights/assert_broadcastable/AssertGuard/Assert/Switch_2", tensor_type=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

Caused by op u'model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape', defined at:
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/runpy.py", line 174, in _run_module_as_main
    "__main__", fname, loader, pkg_name)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/runpy.py", line 72, in _run_code
    exec code in run_globals
  File "/home/rihards/programming/seq2seq/bin/train.py", line 263, in <module>
    tf.app.run()
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "/home/rihards/programming/seq2seq/bin/train.py", line 258, in main
    schedule=FLAGS.schedule)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/learn_runner.py", line 111, in run
    return _execute_schedule(experiment, schedule)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/learn_runner.py", line 46, in _execute_schedule
    return task()
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/experiment.py", line 440, in train_and_evaluate
    self.train(delay_secs=0)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/experiment.py", line 230, in train
    monitors=self._train_monitors + extra_hooks)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/util/deprecation.py", line 281, in new_func
    return func(*args, **kwargs)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 430, in fit
    loss = self._train_model(input_fn=input_fn, hooks=hooks)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 981, in _train_model
    _, loss = mon_sess.run([model_fn_ops.train_op, model_fn_ops.loss])
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 484, in run
    run_metadata=run_metadata)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 821, in run
    run_metadata=run_metadata)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 777, in run
    return self._sess.run(*args, **kwargs)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/training/monitored_session.py", line 939, in run
    run_metadata=run_metadata))
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/monitors.py", line 1155, in after_run
    induce_stop = m.step_end(self._last_step, result)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/monitors.py", line 356, in step_end
    return self.every_n_step_end(step, output)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/monitors.py", line 662, in every_n_step_end
    name=self.name)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/util/deprecation.py", line 281, in new_func
    return func(*args, **kwargs)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 518, in evaluate
    log_progress=log_progress)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 804, in _evaluate_model
    model_fn_results = self._get_eval_ops(features, labels, metrics)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 1163, in _get_eval_ops
    features, labels, model_fn_lib.ModeKeys.EVAL)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 1106, in _call_model_fn
    model_fn_results = self._model_fn(features, labels, **kwargs)
  File "/home/rihards/programming/seq2seq/bin/train.py", line 169, in model_fn
    return model(features, labels, params)
  File "/home/rihards/programming/seq2seq/seq2seq/models/model_base.py", line 112, in __call__
    return self._build(features, labels, params)
  File "/home/rihards/programming/seq2seq/seq2seq/models/seq2seq_model.py", line 262, in _build
    decoder_output, _, = self.decode(encoder_output, features, labels)
  File "/home/rihards/programming/seq2seq/seq2seq/graph_utils.py", line 38, in func_wrapper
    return templated_func(*args, **kwargs)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/ops/template.py", line 277, in __call__
    return self._call_func(args, kwargs, check_for_new_variables=False)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/ops/template.py", line 217, in _call_func
    result = self._func(*args, **kwargs)
  File "/home/rihards/programming/seq2seq/seq2seq/models/basic_seq2seq.py", line 125, in decode
    labels)
  File "/home/rihards/programming/seq2seq/seq2seq/models/basic_seq2seq.py", line 88, in _decode_train
    return decoder(decoder_initial_state, helper_train)
  File "/home/rihards/programming/seq2seq/seq2seq/graph_module.py", line 57, in __call__
    return self._template(*args, **kwargs)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/ops/template.py", line 268, in __call__
    return self._call_func(args, kwargs, check_for_new_variables=False)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/ops/template.py", line 217, in _call_func
    result = self._func(*args, **kwargs)
  File "/home/rihards/programming/seq2seq/seq2seq/decoders/rnn_decoder.py", line 111, in _build
    maximum_iterations=maximum_iterations)
  File "/home/rihards/programming/seq2seq/seq2seq/contrib/seq2seq/decoder.py", line 282, in dynamic_decode
    swap_memory=swap_memory)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2623, in while_loop
    result = context.BuildLoop(cond, body, loop_vars, shape_invariants)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2456, in BuildLoop
    pred, body, original_loop_vars, loop_vars, shape_invariants)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2406, in _BuildLoop
    body_result = body(*packed_vars_for_body)
  File "/home/rihards/programming/seq2seq/seq2seq/contrib/seq2seq/decoder.py", line 242, in body
    decoder_finished) = decoder.step(time, inputs, state)
  File "/home/rihards/programming/seq2seq/seq2seq/decoders/attention_decoder.py", line 167, in step
    self.compute_output(cell_output)
  File "/home/rihards/programming/seq2seq/seq2seq/decoders/attention_decoder.py", line 121, in compute_output
    values_length=self.attention_values_length)
  File "/home/rihards/programming/seq2seq/seq2seq/graph_module.py", line 57, in __call__
    return self._template(*args, **kwargs)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/ops/template.py", line 268, in __call__
    return self._call_func(args, kwargs, check_for_new_variables=False)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/ops/template.py", line 217, in _call_func
    result = self._func(*args, **kwargs)
  File "/home/rihards/programming/seq2seq/seq2seq/decoders/attention.py", line 104, in _build
    scope="att_keys")
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args
    return func(*args, **current_args)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1433, in fully_connected
    outputs = layer.apply(inputs)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/layers/base.py", line 353, in apply
    return self.__call__(inputs, **kwargs)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/layers/base.py", line 323, in __call__
    outputs = self.call(inputs, *args, **kwargs)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/layers/core.py", line 141, in call
    [0]])
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/ops/math_ops.py", line 2378, in tensordot
    a_reshape, a_free_dims, a_free_dims_static = _tensordot_reshape(a, a_axes)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/ops/math_ops.py", line 2345, in _tensordot_reshape
    reshaped_a = array_ops.reshape(array_ops.transpose(a, perm), new_shape)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/ops/gen_array_ops.py", line 2510, in reshape
    name=name)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
    op_def=op_def)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/home/rihards/anaconda2/envs/f27b/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1228, in __init__
    self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 6553600 values, but the requested shape has 0
         [[Node: model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/gpu:0"](model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/transpose, model/att_seq2seq/decode/attention_decoder/decoder/while/attention/att_keys/Tensordot/stack)]]
         [[Node: mean/broadcast_weights/assert_broadcastable/AssertGuard/Assert/Switch_2/_429 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_426_mean/broadcast_weights/assert_broadcastable/AssertGuard/Assert/Switch_2", tensor_type=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

I am running the latest development version of Tensorflow (compiled from source from the master branch). This was to try to solve issue #69 I ran into earlier. I don't know if these things are related.
This was referenced Mar 23, 2017
Closed
Closed
@dennybritz dennybritz mentioned this issue Mar 23, 2017
Closed
@dennybritz
Copy link
Contributor

Thanks for reporting, I do believe all of these issues are caused by the same problem, so I will close them and create a new issue to handle these: #103

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@dennybritz @rihardsk