forked from ecker/DL-Art-School
- Just use resnet blocks for the multiplexer trunk of the generator - Every block initializes itself, rather than everything at the end - Cleans up some messy parts of the architecture, including unnecessary kernel sizes and places where BN is not used properly. |
||
|---|---|---|
| .. | ||
| .idea | ||
| data | ||
| data_scripts | ||
| metrics | ||
| models | ||
| options | ||
| scripts | ||
| temp | ||
| utils | ||
| distill_torchscript.py | ||
| onnx_inference.py | ||
| process_video.py | ||
| recover_tensorboard_log.py | ||
| requirements.txt | ||
| run_scripts.sh | ||
| test.py | ||
| train.py | ||