-
Notifications
You must be signed in to change notification settings - Fork 79
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
saving/loading models #75
Comments
alexnet.cpp and charRNN.cpp have,but error. |
what's error in charRNN.cpp ? |
I had done this test: 2,,before saving paramters, I write these: 3,load paramters like this:
} 4,error like these: I sure that: json for net frame,have no error;but weight parameters don't work well .I didn't know what happen. |
@mz24cn Are U chinese?我英文不太好。要是两个中国人在本土上用英文来探究问题,感觉怪怪的,哈哈哈。 你们用mxnet平台的C++接口实现了几个重要的网络结构,这个工作非常棒!!像caffe上的用prototxt配置文件实现的resnet真是。。。。你们这个用程序逻辑实现的网络结构简洁明了。而且还有rnn。 |
@mz24cn 建议你们: |
charRNN‘s Load/Save is only used as demo for the example. It cannot fit for other examples, nor python predict API except that the net model and parameter names are same as the C++ code. 1,charRNN的Load/Save只是给这个例子用的演示,并不能通用于其他例子,或者python模型的数据。 |
if you can point us to mxnet C api to achieve the same result, it would be helpful, too |
@smissan in src/c_api/c_predict_api.cc line 115,I can find load parameters,this can load paramters that saved parameters by python after train. but I can't find the saving stage that use c/c++. |
Guys,
could you point to the example on how to save/restore model state (weights, not structure)
thanks
The text was updated successfully, but these errors were encountered: