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

Unexpected Results #5

Open
aravindhm opened this issue Feb 26, 2016 · 2 comments
Open

Unexpected Results #5

aravindhm opened this issue Feb 26, 2016 · 2 comments

Comments

@aravindhm
Copy link

I ran the demo code available in python-demo/ folder for the butterfly test image. The output is very different from what is expected based on the publication (ECCV 2014 - https://www.cs.nyu.edu/~fergus/papers/zeilerECCV2014.pdf). It is attached below:-

butterfly_deconvnet

I am using the caffe fork at https://github.com/piergiaj/caffe

make runtest fails at one of the test cases
[ RUN ] NetUpgradeTest.TestUpgradeV1LayerType
/media/data/aravindh/Software/caffe/piergiaj/caffe/src/caffe/test/test_upgrade_proto.cpp:2897: Failure
Value of: V1LayerParameter_LayerType_IsValid(i)
Actual: false
Expected: true
[ FAILED ] NetUpgradeTest.TestUpgradeV1LayerType (1 ms)
[----------] 4 tests from NetUpgradeTest (13 ms total)

@piergiaj
Copy link
Owner

This has to do with the lines that select the features to send back to the input space (roughly line 68 in the demo code):

feat = net.blobs['pool5'].data
feat[0][feat[0] < 150] = 0

If you adjust which features are used, you will get different images.

@GloryZhao
Copy link

Hello @aravindhm
I have the same problem with you.Have you already solved it ?And Can you give me some advises to work it out. 3Q very much.

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

3 participants