search

david-vazquez / mcv-m5

Master in Computer Vision - M5 Visual recognition
13 stars 51 forks source link

YOLO preprocessing issues #31

Open jordi-bird opened 7 years ago

jordi-bird commented 7 years ago

In order to solve the YOLO preprocessing issues in our implementation, we wonder if the imagenet weights employed were created applying pre-processing. If that's the case, we would like confirm if it's the one detailed in data_loader.py as 'imagenet' or any more techniques were used.

Thanks for your time.

lluisgomez commented 7 years ago

@jordi-bird As far as I know the YOLO pre-trained weights are learned without any image pre-processing other than re-scaling the data (with 1./255). This is actually the case for many nets that use batch normalization.

lfrcoder commented 6 years ago

Hello, I saw your work on the mcv-m5 project on github and I feel very good, but there is only code on github, no data and corresponding keras development kit. Can you pass a complete data such as relevant data and keras development kit? thank you very much!