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.

Sign up for GitHub

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

Jump to bottom

Resize features #3

Open

ahmdtaha opened this issue Mar 27, 2020 · 0 comments

ahmdtaha commented Mar 27, 2020

Don't you need to resize AlexNet's feature before training the linear classifier?

Representation-Learning-by-Learning-to-Count/model_classifier.py

Line 109 in 2e86dfe

return fc(tf.reshape(f, [self.batch_size, -1]), self.num_class, is_train,

In [1], check table #2 "the features of each layer are spatially resized until there are fewer than 9K dimensions left"

Also in [2], the author resize AlexNet features
https://github.com/richzhang/colorization/blob/a1642d6ac6fc80fe08885edba34c166da09465f6/feature_learning_tests/linear/train_val.prototxt#L221

[1] Representation Learning-by-Learning-to-Count
[2] Colorful Image Colorization

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment