生成的图片宽高改变CNN验证码训练报错

[xiefg]

tensorflow_cnn 改变图片宽高，训练即失败，代码已定义常量IMAGE_HEIGHT、IMAGE_WIDTH，在此改变无法生效会报错，后面训练相关代码不会自适应图片宽高的改变
Traceback (most recent call last):
File "TensorFlow_cnn_train.py", line 197, in
train_crack_captcha_cnn()
File "TensorFlow_cnn_train.py", line 183, in train_crack_captcha_cnn
, loss = sess.run([optimizer, loss], feed_dict={X: batch_x, Y: batch_y, keep_prob: 0.75})
File "/Library/Python/2.7/site-packages/tensorflow/python/client/session.py", line 778, in run
run_metadata_ptr)
File "/Library/Python/2.7/site-packages/tensorflow/python/client/session.py", line 982, in _run
feed_dict_string, options, run_metadata)
File "/Library/Python/2.7/site-packages/tensorflow/python/client/session.py", line 1032, in _do_run
target_list, options, run_metadata)
File "/Library/Python/2.7/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: Incompatible shapes: [26,315] vs. [64,315]
[[Node: logistic_loss/mul = Mul[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](Add_1, _recv_Placeholder_1_0)]]

Caused by op u'logistic_loss/mul', defined at:
File "TensorFlow_cnn_train.py", line 197, in
train_crack_captcha_cnn()
File "TensorFlow_cnn_train.py", line 165, in train_crack_captcha_cnn
loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=output, labels=Y))
File "/Library/Python/2.7/site-packages/tensorflow/python/ops/nn_impl.py", line 171, in sigmoid_cross_entropy_with_logits
return math_ops.add(relu_logits - logits * labels,
File "/Library/Python/2.7/site-packages/tensorflow/python/ops/math_ops.py", line 821, in binary_op_wrapper
return func(x, y, name=name)
File "/Library/Python/2.7/site-packages/tensorflow/python/ops/math_ops.py", line 1044, in _mul_dispatch
return gen_math_ops._mul(x, y, name=name)
File "/Library/Python/2.7/site-packages/tensorflow/python/ops/gen_math_ops.py", line 1434, in _mul
result = _op_def_lib.apply_op("Mul", x=x, y=y, name=name)
File "/Library/Python/2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
op_def=op_def)
File "/Library/Python/2.7/site-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/Library/Python/2.7/site-packages/tensorflow/python/framework/ops.py", line 1228, in init
self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): Incompatible shapes: [26,315] vs. [64,315]
[[Node: logistic_loss/mul = Mul[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](Add_1, _recv_Placeholder_1_0)]]

[luyishisi]

图片的大小会影响模型中最终输出的shape 你需要在w_d = tf.Variable(w_alpha*tf.random_normal([8*20*64, 1024]))进行修改，，，这里的8和20 是由图片大小 计算而来 60/2/2/2 和 160/2/2/2所得。你也应该尝试修改

[xiefg]

多谢，早上已经修正，确实是这个需要变更