forked from ecker/DL-Art-School
- Add filters_mid spec which allows a expansion->squeeze for the transformation layers. - Add scale and bias AFTER the switch - Remove identity transform (models were converging on this) - Move attention image generation and temperature setting into new function which gets called every step with a save path |
||
|---|---|---|
| .. | ||
| .idea | ||
| data | ||
| data_scripts | ||
| metrics | ||
| models | ||
| options | ||
| scripts | ||
| temp | ||
| utils | ||
| distill_torchscript.py | ||
| onnx_inference.py | ||
| process_video.py | ||
| requirements.txt | ||
| run_scripts.sh | ||
| test.py | ||
| train.py | ||