lllcho / captcha-breaking Goto Github PK

View Code? Open in Web Editor NEW

225.0 225.0 82.0 81.49 MB

License: MIT License

Python 100.00%

captcha-breaking's People

Contributors

Stargazers

Watchers

Forkers

willchiang7378 zhaorenjie110 bacjiang vincent-poon jiaweisong hopef chdd jinhang duum moonlightlong guodao xyz8 kingjci sunqipeng-cn yidun55 newaynewlife lixiaosi33 hikylemorris ldy321 shuxin yfzyl tsintian aialbert lordrings104 boot-strap-leo shikigit flourishing icemage001 bighaidao 0xa-saline prm10 purplehua wzwyoyo sunlaobo wxq92109 feng520893 zhaodonghui3939 mapbased campuslifeceo dancinghui humek chen-ying-v awesome-archive sunyunyun foxsugar alonelaval khronosplus w906022793 khronosplusplus liuhuiwisdom wsbmilk leoluyi smilemilk1992 moyhspider hi-ylf tinalei scottdu jerusalemsbell incenter2016 badaozhai strongc liangsi03 tutty427 xmduhan l121503258 rosssong jeremyzhang866 xaiomoqing wolfwhoami babylls mohamadeq juzenn chenbocqu zinc-30 zaijianyingmu yishuihanhan kivvf fakegit moonight10 zfy1989lee hell-to-heaven salagrie

captcha-breaking's Issues

issue

TypeError: Layer can receive at most 3 positional arguments.这个应该怎么改呢，谢谢

楼主有没有相关博客笔记之类的？

感谢开源，代码很有参考价值，如果能加点解读和笔记之类的就更好了。比如预处理那块是怎么做的。

nb_model.add(Convolution2D(32, 1, 4, border_mode='full', activation='relu', W_regularizer=l2(weight_decay)))报错

您好大神，现在无法运行，是因为keras版本跟新的问题么？
TypeError: Layer can receive at most 3 positional arguments.
ValueError: The padding argument must be one of "valid", "same" (or "causal" for Conv1D). Received: full
小白不太懂，请问怎么修改呢？

训练模型源码

恳请大虾能够共享训练模型源码。
在下默默搜了2天资料，终于搜索到了大虾的源码，深感震惊！（本人计算机专业，对这些一无所知，本以为只是一些简单处理），同时也庆幸有了希望。无奈，没有基础，自己学习了7天还是没能写出训练模型的代码。希望大虾帮帮忙...将源码发布或发送到[email protected]
临表涕零！感激不尽！

想询问参考书籍

你好如果是完全新手想学会用keras
有什麽机器学习的书或是网络资源能参考的吗

请教下全连接层输出的结果是怎么计算的。

model = Sequential()
model.add(Convolution2D(32, 1, 4, 4, border_mode='full', activation='relu'))
model.add(Convolution2D(32, 32, 4, 4, activation='relu'))
model.add(MaxPooling2D(poolsize=(3, 3)))
model.add(Dropout(0.25))
model.add(Convolution2D(64, 32, 4, 4, border_mode='full', activation='relu'))
model.add(Convolution2D(64, 64, 4, 4, activation='relu'))
model.add(MaxPooling2D(poolsize=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(64 * 5 * 5, 512, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(512, nb_class, activation='softmax'))
model.load_weights(model_path)

model.compile(loss='categorical_crossentropy', optimizer='adagrad')

请教下上面的model.add(Dense(64 * 5 * 5, 512, activation='relu'))中的5*5是怎么计算出来的。小白，先谢过

Traceback (most recent call last):
  File "./test_type1.py", line 35, in <module>
    model_ch.compile(loss='categorical_crossentropy', optimizer='adagrad')
  File "build/bdist.linux-x86_64/egg/keras/models.py", line 351, in compile
  File "build/bdist.linux-x86_64/egg/keras/layers/containers.py", line 53, in get_output
  File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 388, in get_output
  File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 32, in get_input
  File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 228, in get_output
  File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 32, in get_input
  File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 388, in get_output
  File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 32, in get_input
  File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 309, in get_output
  File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 32, in get_input
  File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 228, in get_output
  File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 32, in get_input
  File "build/bdist.linux-x86_64/egg/keras/layers/convolutional.py", line 209, in get_output
  File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 32, in get_input
  File "build/bdist.linux-x86_64/egg/keras/layers/convolutional.py", line 168, in get_output
  File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 32, in get_input
  File "build/bdist.linux-x86_64/egg/keras/layers/convolutional.py", line 168, in get_output
  File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 32, in get_input
  File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 228, in get_output
  File "build/bdist.linux-x86_64/egg/keras/layers/core.py", line 32, in get_input
  File "build/bdist.linux-x86_64/egg/keras/layers/convolutional.py", line 210, in get_output
AttributeError: 'module' object has no attribute 'downsample'

训练模型的程序可以分享吗

嘻嘻

lllcho / captcha-breaking Goto Github PK

captcha-breaking's People

Contributors

Stargazers

Watchers

Forkers

captcha-breaking's Issues

model.compile(loss='categorical_crossentropy', optimizer='adagrad')

Recommend Projects

Recommend Topics

Recommend Org

Jobs