Can not reproduce the result using default option and model

Maclory / Deep-Iterative-Collaboration

Pytorch implementation of Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimation (CVPR 2020)

MIT License

295 stars 63 forks source link

Can not reproduce the result using default option and model #2

Closed Glorainow closed 4 years ago

Glorainow commented 4 years ago

I changed the pathes of model and images in the test_DICGAN_Helen.json and test_DIC_Helen.json, then ran test.py use these options as told in README. But the results are really terrrible. Did I miss something? The data used to test the program is Helen that downloaded as asked and preprocessed as said in https://github.com/Maclory/Deep-Iterative-Collaboration/issues/1. The models I used were DIC_Helen.pth and DICGAN_Helen.pth respectively.

Maclory commented 4 years ago

Hi, we have uploaded our testing sets of CelebA and Helen to Google Drive and Baidu Drive (extraction code: 6qhx). We will also upload our code for data preprocessing soon.