orange90 / handwrittenchineserecogntion Goto Github PK

I have read your code, and tried to make some experiments on HWDB1. I noticed that when I choose adam as optimizer and didn't set learn_rate myself, the train_acc fluctuated near 1/3755. On the contrary, the model kept improving when I set a learning rate scheme for it. How did you make it with neither set parameters for the optimizer nor set a learning rate?
您好，我看了您的代码并打算在HWDB1上做些实验。在直接使用adam的时候，训练模型的时候训练的acc会一直在1/3755附近波动，但是我后来自己设置lr后模型可以正常训练了。想问问您是怎么做到在不设置optimizer参数的情况下做到模型能正常训练的。谢谢。

• 楼主你好，加载你的模型后，我是通过predict()方法预测，得到的array 长度3755，根据最大值的索引对比汉字，很多都不对；
• 想问下楼主，上面我尝试的方法是否正确，那输入一张单字手写图片，怎么预测输出标签结果呢？可以代码示例吗？

Got error when debugging convert_data.py, can you please help out? Thanks.

D:\DEV\Python\Envs\DLPy36\Scripts\python.exe "C:\Program Files (x86)\JetBrains\PyCharm 4.5.4\helpers\pydev\pydevd.py" --multiproc --client 127.0.0.1 --port 56353 --file D:/DEV/Python/CodeBase/hanzishibie/HandWrittenChineseRecogntion-master/convert_data.py
pydev debugger: process 11904 is connecting

Connected to pydev debugger (build 141.2569)
0
start extracting training data
start extracting testing data
Traceback (most recent call last):
File "C:\Program Files (x86)\JetBrains\PyCharm 4.5.4\helpers\pydev\pydevd.py", line 2358, in
globals = debugger.run(setup['file'], None, None, is_module)
File "C:\Program Files (x86)\JetBrains\PyCharm 4.5.4\helpers\pydev\pydevd.py", line 1778, in run
pydev_imports.execfile(file, globals, locals) # execute the script
File "C:\Program Files (x86)\JetBrains\PyCharm 4.5.4\helpers\pydev_pydev_imps_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "D:/DEV/Python/CodeBase/hanzishibie/HandWrittenChineseRecogntion-master/convert_data.py", line 67, in
dir_name = './data/test/' + '%0.5d'%char_dict[tagcode_unicode]
KeyError: '啊'

Process finished with exit code -1