rfelixmg / frwgan-eccv18

Code for model presented on our paper accepted on European Conference on Computer Vision 2018.
57 stars 23 forks source link

Generated Features #12

Closed thecomsian closed 4 years ago

thecomsian commented 4 years ago

Hello @rfelixmg

Thank for providing the Amazing Implementation!!!.

I faced the problem of symlink and solved it by reading #11 .

I am beginner and I have some questions.

  1. Is there anyway to resume epochs from the point where it is stopped?

  2. When I executed, generate_dataset.sh, Output shows, Generating seen and Unseen features and dataset .h5 file is created. How to analyze this H5, How to figure out that unseen feature have been generated, Is there any way to seen them.

Thanks,

rfelixmg commented 4 years ago

@thecomsian tks!

Do you mean re-training\fine-tunning the model? You will find more on --there is a way to re-train or further train the model [--load_model LOAD_MODEL]

python main.py --help

Yes, there is a way to analyse the features generated (bare in mind, they are only resnet features R^{2048}. Hence, they are not highly interpretable.

You can use a software name H5view, which is a free tool that you can find more about here https://www.neonscience.org/explore-data-hdfview and here https://support.hdfgroup.org/products/java/release/download.html

Best wishes, Rafa.