jack-cherish / deep-learning Goto Github PK

大神您好，请问这个是在那个文件夹呀，我看了tutorials里面有一个minist，可是我没找到input_data呀，然后run的时候也说没有这个，谢谢您呀

123

请问下，我用深度学习训练了一些英数验证码，然后得到一个模型，过了一段时间之后，我又有了新得风格的样本，可以在原来的模型上继续训练吗，如果在原来的模型使用新的样本继续训练的话， 最后得到的模型，还能识别以前的那些风格的验证码
如果 50万张样本，100多种类型的验证码，能不能训练出来一个通用的模型出来

Hello, I found a performance issue in the definition of crack_captcha, Discuz/test.py, tf.argmax and tf.reshape will be created repeatedly during the program execution. It will add extra node in the graph(tensorflow 1.x). I think it should be created before the loo in the crack_captcha.

Looking forward to your reply. Btw, I am very glad to create a PR to fix it if you are too busy.

你好，该代码能进行多分类吗（比如4分类）？麻烦博主可以指导一下吗？直接修改n_classes=4报错了，期待你的回复

看一下你的博客，电脑烫到飞起，chrome瞬间cpu占用40% ， 关掉之后就调到0了，
用大家的电脑挖矿请提前说一声谢谢

您好，感谢您的分享。我在运行代码时遇到了以下问题，在网上没有找到解决办法，可以帮我看一下该如何解决吗？
Traceback (most recent call last):
File "F:/pythonProject/Unet/Lib/dataset.py", line 44, in
isbi_dataset = ISBI_Loader("C:/Users/Administrator/Desktop/Segmentation/Unet/data/data/train/")
File "F:\Anaconda3\lib\typing.py", line 875, in new
obj = super().new(cls, *args, **kwds)
TypeError: object.new() takes exactly one argument (the type to instantiate)

为何不用tensorflow进行图像灰度处理，而用plt。

谢谢作者大大！！

Discuz训练代码我改成训练其他字符验证码，改了数据路径与图片大小，请问这种报错是什么原因呢？

2018-12-25 06:42:58.270255: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
Traceback (most recent call last):
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1292, in _do_call
return fn(*args)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1277, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1367, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 761600 values, but the requested shape requires a multiple of 3328
[[{{node Reshape_1}} = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"](MaxPool_2, Reshape_1/shape)]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "./train.py", line 388, in
m.train_crack_captcha_cnn()
File "./train.py", line 361, in train_crack_captcha_cnn
summary, acc = sess.run([merged, accuracy], feed_dict={self.X: batch_x_test, self.Y: batch_y_test, self.keep_prob: 1})
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 887, in run
run_metadata_ptr)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1110, in _run
feed_dict_tensor, options, run_metadata)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1286, in _do_run
run_metadata)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1308, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 761600 values, but the requested shape requires a multiple of 3328
[[{{node Reshape_1}} = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"](MaxPool_2, Reshape_1/shape)]]

Caused by op 'Reshape_1', defined at:
File "./train.py", line 388, in
m.train_crack_captcha_cnn()
File "./train.py", line 327, in train_crack_captcha_cnn
model = self.crack_captcha_cnn()
File "./train.py", line 305, in crack_captcha_cnn
dense = tf.reshape(conv3, [-1, w_d.get_shape().as_list()[0]])
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 6296, in reshape
"Reshape", tensor=tensor, shape=shape, name=name)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
return func(*args, **kwargs)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3272, in create_op
op_def=op_def)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1768, in init
self._traceback = tf_stack.extract_stack()

InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 761600 values, but the requested shape requires a multiple of 3328
[[{{node Reshape_1}} = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"](MaxPool_2, Reshape_1/shape)]]

运行环境 windows10 python 3.7.2
cpu g4400

看文章转载可以，但为什么直接github上显示是自己的教程并且代码也基本一样？

https://github.com/Jack-Cherish/Deep-Learning

为什么在最后的分类函数中使用sigmoid函数分类，这个不是用来做二分类的吗？应该是使用softmax函数吧，而且修改为softmax函数之后再运行会发现loss会一直上升，所以我不知道问题出现在哪儿了？