0prrr/chinese-novel-generation

DEPRECATED 尝试使用中文文本训练RNN来产生中文小说。（No longer under maintanance.）

DEPRECATED

This is no longer under maintainance due to the change of Tensorflow version. If you tend to use the code, please ensure to run under TF version 1.0, any higher version needs proper adjustment of the code.

Chinese-novel-generation

基于Tensorflow 1.0.0，尝试使用中文文本训练RNN来产生中文小说。

博客地址: http://blog.csdn.net/heisejiuhuche/article/details/73010638

chinese-novel-generation's Issues

运行报错，这是什么原因

D:\python3.6-64\python.exe C:/Users/Notebook/Chinese-novel-generation/test.py
WARNING:tensorflow:From D:\python3.6-64\lib\site-packages\tensorflow\contrib\learn\python\learn\datasets\base.py:198: retry (from tensorflow.contrib.learn.python.learn.datasets.base) is deprecated and will be removed in a future version.
Instructions for updating:
Use the retry module or similar alternatives.
Traceback (most recent call last):
File "D:\python3.6-64\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 686, in _call_cpp_shape_fn_impl
input_tensors_as_shapes, status)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 516, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 512 and 556 for 'rnn/while/rnn/multi_rnn_cell/cell_0/basic_lstm_cell/MatMul_1' (op: 'MatMul') with input shapes: [?,512], [556,1024].

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:/Users/Notebook/Chinese-novel-generation/test.py", line 214, in
logits, final_state = build_nn(cell, rnn_size, input_text, vocab_size, embed_dim)
File "C:/Users/Notebook/Chinese-novel-generation/test.py", line 149, in build_nn
outputs, final_state = build_rnn(cell, embed)
File "C:/Users/Notebook/Chinese-novel-generation/test.py", line 136, in build_rnn
outputs, final_state = tf.nn.dynamic_rnn(cell, inputs, dtype=tf.float32)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\ops\rnn.py", line 635, in dynamic_rnn
dtype=dtype)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\ops\rnn.py", line 832, in _dynamic_rnn_loop
swap_memory=swap_memory)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\ops\control_flow_ops.py", line 3202, in while_loop
result = loop_context.BuildLoop(cond, body, loop_vars, shape_invariants)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\ops\control_flow_ops.py", line 2940, in BuildLoop
pred, body, original_loop_vars, loop_vars, shape_invariants)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\ops\control_flow_ops.py", line 2877, in _BuildLoop
body_result = body(*packed_vars_for_body)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\ops\control_flow_ops.py", line 3178, in
body = lambda i, lv: (i + 1, orig_body(*lv))
File "D:\python3.6-64\lib\site-packages\tensorflow\python\ops\rnn.py", line 803, in _time_step
(output, new_state) = call_cell()
File "D:\python3.6-64\lib\site-packages\tensorflow\python\ops\rnn.py", line 789, in
call_cell = lambda: cell(input_t, state)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\ops\rnn_cell_impl.py", line 191, in call
return super(RNNCell, self).call(inputs, state)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\layers\base.py", line 714, in call
outputs = self.call(inputs, *args, **kwargs)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\ops\rnn_cell_impl.py", line 1242, in call
cur_inp, new_state = cell(cur_inp, cur_state)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\ops\rnn_cell_impl.py", line 1058, in call
output, new_state = self._cell(inputs, state, scope=scope)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\ops\rnn_cell_impl.py", line 298, in call
*args, **kwargs)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\layers\base.py", line 714, in call
outputs = self.call(inputs, *args, **kwargs)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\ops\rnn_cell_impl.py", line 579, in call
array_ops.concat([inputs, h], 1), self._kernel)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\ops\math_ops.py", line 2108, in matmul
a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\ops\gen_math_ops.py", line 4492, in mat_mul
name=name)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\framework\ops.py", line 3292, in create_op
compute_device=compute_device)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\framework\ops.py", line 3332, in _create_op_helper
set_shapes_for_outputs(op)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\framework\ops.py", line 2496, in set_shapes_for_outputs
return _set_shapes_for_outputs(op)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\framework\ops.py", line 2469, in _set_shapes_for_outputs
shapes = shape_func(op)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\framework\ops.py", line 2399, in call_with_requiring
return call_cpp_shape_fn(op, require_shape_fn=True)
File "D:\python3.6-64\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 627, in call_cpp_shape_fn
require_shape_fn)
File "D:\python3.6-64\lib\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 512 and 556 for 'rnn/while/rnn/multi_rnn_cell/cell_0/basic_lstm_cell/MatMul_1' (op: 'MatMul') with input shapes: [?,512], [556,1024].

参数问题

我想问一下，我运行的时候少了一个param.p的文件，是为啥

Error

发现在 get_init_cell 中，应该将cell的定义修改如下：
def make_cell():
cell = tf.contrib.rnn.BasicLSTMCell(rnn_size)
if keep_prob < 1:
cell = tf.contrib.rnn.DropoutWrapper(cell, output_keep_prob=keep_prob)
return cell

cell = tf.contrib.rnn.MultiRNNCell([make_cell() for _ in range(num_layers)])