captcha-tensorflow icon indicating copy to clipboard operation
captcha-tensorflow copied to clipboard

hack captcha by cnn with tensorflow

Results 5 captcha-tensorflow issues
Sort by recently updated
recently updated
newest added

如果最终要预测的是四个字符,把loss定义为四部分交叉熵loss的平方和(每部分label是一个one-hot向量),效果会显著提升,现在这样直接把输出结果和一个four-hot向量做交叉熵,意义不大

我做的是单个字符的验证码识别,用softmax_cross_entropy_with_logits计算loss时,loss降到3.5左右就不再变化,改用sigmoid_cross_entropy_with_logits后loss会下降到0.15左右就不再下降,这是什么原因呢?

训练时把生成的图片高改成了70就报错了,错误如下: Caused by op 'my_monitor/softmax_cross_entropy_with_logits_sg', defined at: File "D:/workspace-python/captcha-tensorflow-master/capt/train.py", line 104, in train_crack_captcha_cnn() File "D:/workspace-python/captcha-tensorflow-master/capt/train.py", line 26, in train_crack_captcha_cnn loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=predict, labels=label)) File "D:\softs\Anaconda3\envs\app_002\lib\site-packages\tensorflow\python\util\deprecation.py", line 250, in new_func return...

错误提示信息: 'JpegImageFile' object has no attribute 'shape'

请问一下,你的数据集具体给了多大?谢谢