Skip to content
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

How is the 128(BATCH_SIZE) RoIs sent to ID net #113

Open
DaisyJiao opened this issue Aug 27, 2018 · 0 comments
Open

How is the 128(BATCH_SIZE) RoIs sent to ID net #113

DaisyJiao opened this issue Aug 27, 2018 · 0 comments

Comments

@DaisyJiao
Copy link

For example, in the training log,
I0816 01:36:36.621873 36439 layer_factory.hpp:74] Creating layer feat_lowdim
I0816 01:36:36.621896 36439 net.cpp:99] Creating Layer feat_lowdim
I0816 01:36:36.621906 36439 net.cpp:479] feat_lowdim <- caffe.Pooling_168_caffe.Pooling_168_0_split_2
I0816 01:36:36.621978 36439 net.cpp:130] This layer is inheriting previous layer's sync mode: 1
I0816 01:36:36.621999 36439 net.cpp:435] feat_lowdim -> feat_lowdim
I0816 01:36:36.622017 36439 net.cpp:163] Setting up feat_lowdim
I0816 01:36:36.625612 36439 net.cpp:170] Top shape: 1 256 (256)

The top shape of identification net is 1N instead of 128N.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant