pyronear / pyro-vision

Computer vision library for wildfire detection 🌲 Deep learning models in PyTorch & ONNX for inference on edge devices (e.g. Raspberry Pi)
https://pyronear.org/pyro-vision/
Apache License 2.0
52 stars 24 forks source link

fix: Fixed rexnet1_3x and rexnet1_5x and updated checkpoints #164

Closed frgfm closed 2 years ago

frgfm commented 2 years ago

This PR introduces the following modifications:

Any feedback is welcome!

codecov[bot] commented 2 years ago

Codecov Report

Merging #164 (458ac8b) into master (6d88202) will decrease coverage by 0.02%. The diff coverage is 100.00%.

@@            Coverage Diff             @@
##           master     #164      +/-   ##
==========================================
- Coverage   93.88%   93.85%   -0.03%     
==========================================
  Files           9        9              
  Lines         229      228       -1     
==========================================
- Hits          215      214       -1     
  Misses         14       14              
Flag Coverage Δ
unittests 93.85% <100.00%> (-0.03%) :arrow_down:

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files Coverage Δ
pyrovision/models/mobilenetv3.py 100.00% <ø> (ø)
pyrovision/models/resnet.py 100.00% <ø> (ø)
pyrovision/datasets/utils.py 88.57% <100.00%> (-0.17%) :arrow_down:
pyrovision/models/rexnet.py 100.00% <100.00%> (ø)

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

MateoLostanlen commented 2 years ago

Hi @frgfm just a question did you use readme parameters for all models ? If not, it would be nice to add them to the performance table to keep track

frgfm commented 2 years ago

@MateoLostanlen I kept everything, but the args are not always the same from one model to the other. So we'll have to think about how to keep track of that & share it

frgfm commented 2 years ago

I just updated the readme instruction to display the command I use most often :+1: