DL-Art-School/codes
James Betker 407224eba1 Re-work SwitchedResgen2
Got rid of the converged multiplexer bases but kept the configurable architecture. The
new multiplexers look a lot like the old one.

Took some queues from the transformer architecture: translate image to a higher filter-space
and stay there for the duration of the models computation. Also perform convs after each
switch to allow the model to anneal issues that arise.
2020-06-25 18:17:05 -06:00
..
.idea IDEA update 2020-05-19 09:35:26 -06:00
data Add doResizeLoss to dataset 2020-06-08 11:27:06 -06:00
data_scripts Add simple resize to extract images 2020-06-23 09:39:51 -06:00
metrics mmsr 2019-08-23 21:42:47 +08:00
models Re-work SwitchedResgen2 2020-06-25 18:17:05 -06:00
options Add dynamic video processing script 2020-05-27 17:09:11 -06:00
scripts mmsr 2019-08-23 21:42:47 +08:00
temp Misc changes 2020-05-14 20:45:38 -06:00
utils Add GPU mem tracing module 2020-06-14 11:02:54 -06:00
distill_torchscript.py Misc 2020-06-14 11:03:02 -06:00
onnx_inference.py Misc 2020-06-14 11:03:02 -06:00
process_video.py Debug process_video 2020-05-29 20:44:50 -06:00
requirements.txt Introduce (untested) colab mode 2020-06-01 15:09:52 -06:00
run_scripts.sh mmsr 2019-08-23 21:42:47 +08:00
test.py Misc 2020-06-02 09:35:52 -06:00
train.py Log tensorboard directly into experiments directory 2020-06-18 11:33:02 -06:00