ycg09 / tf-text-classification Goto Github PK

The program would raise ValueError when running text_rnn.py. I'm using anaconda with tensorflow 1.5.0.
The details are as follows:
Command:
python text_rnn.py
Results:
Traceback (most recent call last):
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py", line 686, in _call_cpp_shape_fn_impl
input_tensors_as_shapes, status)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 473, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 200 and 250 for 'bi_rnn/bidirectional_rnn/fw/fw/while/fw/multi_rnn_cell/cell_0/gru_cell/MatMul_2' (op: 'MatMul') with input shapes: [?,200], [250,200].

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/Users/myname/Documents/python/attrnn/text_rnn.py", line 123, in
attention_size=50, num_classes=30, learning_rate=0.001, grad_clip=5.0)
File "/Users/myname/Documents/python/attrnn/text_rnn.py", line 64, in init
sequence_length=self.seq_len, dtype=tf.float32)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 414, in bidirectional_dynamic_rnn
time_major=time_major, scope=fw_scope)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 629, in dynamic_rnn
dtype=dtype)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 820, in _dynamic_rnn_loop
swap_memory=swap_memory)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2934, in while_loop
result = loop_context.BuildLoop(cond, body, loop_vars, shape_invariants)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2720, in BuildLoop
pred, body, original_loop_vars, loop_vars, shape_invariants)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2662, in _BuildLoop
body_result = body(*packed_vars_for_body)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2913, in
body = lambda i, lv: (i + 1, orig_body(*lv))
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 793, in _time_step
skip_conditionals=True)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 248, in _rnn_step
new_output, new_state = call_cell()
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 781, in
call_cell = lambda: cell(input_t, state)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/rnn_cell_impl.py", line 1042, in call
output, new_state = self._cell(inputs, state, scope=scope)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/rnn_cell_impl.py", line 188, in call
return super(RNNCell, self).call(inputs, state)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/layers/base.py", line 652, in call
outputs = self.call(inputs, *args, **kwargs)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/rnn_cell_impl.py", line 1217, in call
cur_inp, new_state = cell(cur_inp, cur_state)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/rnn_cell_impl.py", line 292, in call
*args, **kwargs)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/layers/base.py", line 652, in call
outputs = self.call(inputs, *args, **kwargs)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/rnn_cell_impl.py", line 429, in call
array_ops.concat([inputs, state], 1), self._gate_kernel)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 2022, in matmul
a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 2516, in _mat_mul
name=name)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3162, in create_op
compute_device=compute_device)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3208, in _create_op_helper
set_shapes_for_outputs(op)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2427, in set_shapes_for_outputs
return _set_shapes_for_outputs(op)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2400, in _set_shapes_for_outputs
shapes = shape_func(op)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2330, in call_with_requiring
return call_cpp_shape_fn(op, require_shape_fn=True)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py", line 627, in call_cpp_shape_fn
require_shape_fn)
File "/Users/myname/anaconda2/envs/tf/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py", line 691, in _call_cpp_shape_fn_impl
raise ValueError(err.message)
ValueError: Dimensions must be equal, but are 200 and 250 for 'bi_rnn/bidirectional_rnn/fw/fw/while/fw/multi_rnn_cell/cell_0/gru_cell/MatMul_2' (op: 'MatMul') with input shapes: [?,200], [250,200].

Process finished with exit code 1

So could anyone tell me where should I change to solve this problem? Thanks in advance.

Hi,

Is it possible to add a (small) file with some example data? I have no clue what to put in ./data/traindata

Kind regards