1、这是在巡行train文件时候提示的错误
问题:InvalidArgumentError (see above for traceback): Input to reshape is a tensor wit
h 8192 values, but the requested shape requires a multiple of 384
[[Node: Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:lo
输出提示信息为:
calhost/replica:0/task:0/cpu:0"](concat, Reshape/shape)]]
、Traceback (most recent call last):
File "train.py", line 193, in
train_step(x_batch, y_batch)
File "train.py", line 164, in train_step
feed_dict)
File "d:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\client
session.py", line 778, in run
run_metadata_ptr)
File "d:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\client
session.py", line 982, in _run
feed_dict_string, options, run_metadata)
File "d:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\client
session.py", line 1032, in _do_run
target_list, options, run_metadata)
File "d:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\client
session.py", line 1052, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape i
s a tensor with 8192 values, but the requested shape requires a multiple of 384
[[Node: Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:lo
calhost/replica:0/task:0/cpu:0"](concat, Reshape/shape)]]
Caused by op 'Reshape', defined at:
File "train.py", line 108, in
l2_reg_lambda = FLAGS.l2_reg_lambda)
File "C:\Users\Administrator\PycharmProjects\zh_cnn_text_classify-master\text_
cnn.py", line 56, in init
self.h_pool_flat = tf.reshape(self.h_pool, [-1, num_filters_total])
File "d:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\gen
_array_ops.py", line 2510, in reshape
name=name)
File "d:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\framewo
rk\op_def_library.py", line 768, in apply_op
op_def=op_def)
File "d:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\framewo
rk\ops.py", line 2336, in create_op
original_op=self._default_original_op, op_def=op_def)
File "d:\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\framewo
rk\ops.py", line 1228, in init
self._traceback = _extract_stack()
InvalidArgumentError (see above for traceback): Input to reshape is a tensor wit
h 8192 values, but the requested shape requires a multiple of 384
[[Node: Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:lo
calhost/replica:0/task:0/cpu:0"](concat, Reshape/shape)]]
2、在运行eval文件中input_label_file这个参数如何设置?
本人对这方面感兴趣,麻烦作者帮忙解决!!!