-
Notifications
You must be signed in to change notification settings - Fork 23
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
the weight of InnerProduct layer #4
Comments
是1024乘以1024乘以1024乘以10的全连接 |
@pengjiao123 默认存储的是全精度的权重,使用时按照三值化函数前馈传播就行了。在deploy的时候,可以存储为三值化的权重,需要在solver里面加上 |
的确会额外生成如lenet_tn_iter_1000.caffemodel.tn的文件,但是无法读取。一般的caffemodel不是可以通过net = caffe.Net(model, weights, 'test')的方式提取参数吗?我试了用这种方法不行。 |
存储的时候是把 16 个三值参数打包成 1 个 fixed32 类型的 ProtoBuffer, 所以需要专门的功能函数读取。你可以参考下 TernaryToProto 和 TernaryFromProto 这两个函数(blobs, layer, nets中)。 |
您好,请问你有解决掉读取三值权重模型这个问题吗? |
Hi @pengjiao123, are you able to visualize the ternary weights. Because i tried caffe code but that didn't work for me. |
你好,我把网络连接改成102410241024*10的全连接,利用python接口拿出solver.net.params['ip1'][0].data
即为全连接层的权重,为什么不是三值的?是不是我哪里做的有问题?
The text was updated successfully, but these errors were encountered: