-
Notifications
You must be signed in to change notification settings - Fork 18.7k
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
Problem with Fillers in matcaffe in OSX #178
Comments
Sergio, you already raised this issue in #175. Please close one of these. |
Also, I'm afraid you're not even on |
@shelhamer sorry for the confusion with imagenet_deploy.prototxt and imagenet.prototxt. I know there is no imagenet_deploy.prototxt anymore, but imagenet.prototxt doesn't currently work (since it include the fillers) with matcaffe, so I created a temporal imagenet_deploy.prototxt which doesn't include fillers, but then I get a problem when restoring the net due to the dimensions. |
@shelhamer I'm tracking down the error, it seems that it is related to OSX, since in Ubuntu it doesn't happen. If one removes the fillers from imagenet.prototxt then matcaffe_demo works in OSX, otherwise it doesn't. Although it takes a lot of time to set_mode to CPU (I cannot test GPU due to memory constraints), while it should be fast since class Caffe is a singleton (isn't it? @Yangqing). These problems don't happen in Ubuntu. Once the mode is set it is fast to process the images. |
@Yangqing the part of the code that make it slow is the initialization of CUBLAS in
Does anyone knows why this happen? This makes matlab to use 300MB extra of memory. When in reality it is never used in CPU mode. |
@sguada is this still a problem or ancient history? |
Multi-GPU support for the GPUMemory::Workspace
This is a weird problem.
When using imagenet_deploy.txt containing
weight_filler
and/orbias_filler
in a layer then thenet.init()
process don't continue.When not using
weight_filler
and/orbias_filler
in the layers thennet.init()
works well but then when restoring the trained model there is dimension mismatch in fc6 layer.The text was updated successfully, but these errors were encountered: