moxiegushi / zhihu Goto Github PK

如题，谢谢！

Traceback (most recent call last):
File "zhihu.py", line 180, in
state = login()
File "zhihu.py", line 63, in login
data['captcha'] = predict(cropModel,classModel)
File "zhihu.py", line 94, in predict
predictCrop = cropModel.predict_generator(cropGenerator,121)
File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.2-py2.7.egg/keras/models.py", line 981, in predict_generator
pickle_safe=pickle_safe)
File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.2-py2.7.egg/keras/engine/training.py", line 1652, in predict_generator
outs = self.predict_on_batch(x)
File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.2-py2.7.egg/keras/engine/training.py", line 1273, in predict_on_batch
self.internal_input_shapes)
File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.2-py2.7.egg/keras/engine/training.py", line 73, in standardize_input_data
'Found: ' + str(data)[:200] + '...')
Exception: Error when checking : data should be a Numpy array, or list/dict of Numpy arrays. Found: None...

list indext out of range.debug 发现maping是0-121,index长度3632,想请教下这个错误该如何修正

训练crop时，flow_from_directory()自动导入0类（crop不成功的）和1类（crop好的）作为两类训练数据？
但是训练单个字母分类时，单个字母的target label并没有啊，这个部分是怎么训练出来的？

Traceback (most recent call last):
File "/Users/druw_shark/PycharmProjects/keras-zhihu-master-ForEasyDeepLeaning/zhihu.py", line 179, in
cropModel = load_model(crop_model)
File "/Library/Python/2.7/site-packages/keras/models.py", line 280, in load_model
model.optimizer.set_weights(optimizer_weight_values)
File "/Library/Python/2.7/site-packages/keras/optimizers.py", line 79, in set_weights
'provided weight shape ' + str(w.shape))
ValueError: Optimizer weight shape (4,) not compatible with provided weight shape (3, 3, 1, 4)

['11.png', '44.png', '73.png', '106.png']
Traceback (most recent call last):
File "zhihu.py", line 180, in
state = login()
File "zhihu.py", line 63, in login
data['captcha'] = predict(cropModel,classModel)
File "zhihu.py", line 121, in predict
temp.save('./tobe_classfied/data/' + each)
File "/Library/Python/2.7/site-packages/PIL/Image.py", line 1659, in save
fp = builtins.open(filename, "wb")
IOError: [Errno 2] No such file or directory: './tobe_classfied/data/11.png'

还有数据集的标签之类的，谢谢~

初涉人工智能，如果您能详细讲解下训练的过程的话，感激不尽！