See wiki for more details and further results.
cae_32x32x32_zero_pad_bin model, after roughly 5.8 millions of optimization steps;
left: original, right: reconstructed.
A smaller dataset (2,286 frames) that I have used in the Further results page of the wiki can be downloaded here.
A bigger dataset can be constructed by downloading frames using the scripts provided here. For the above results, I have randomly selected and downloaded 121,827 frames.
- GTX 1080 Ti (with 11GB graphic memory)
- Ubuntu 16.04
- Python 3.5
- Cuda 9.0
- Pytorch 0.4.1
python3 train.py --exp_name Kodak --shuffle --dataset ./dataset/Kodak
python3 test.py --chkpt ./checkpoints/Kodak/model_final.state --shuffle --dataset_path ./dataset/Kodak --out_dir ./Kodak