EfficientDet.Pytorch
EfficientDet.Pytorch copied to clipboard
Training on custom dataset (9 classes)
Hi,
I am facing issue in biFpn module while starting the training using pretrained d1.
File "train.py", line 238, in
Input Size : (640,640) Num Classes : 9
The data loaded is in the same format as the COCO.
Can you please help what am I doing wrong?
Am also seeing the same issue. Were you able to resolve this issue?
I changed the scale_factor=3 to scale_factor=2. I was able to start the training. I don't know what it is used for.
Not sure which version of the model file you are using, but I see that scale_factor is set as 2 already. From a quick look, scale_factor seems to be the upsampling factor for the feature maps.
I was trying to run the eval.py script. Seems like the augmentation is not set properly for the validation phase (in the version of the code I checked in). The issue I was facing is fixed in the commit: https://github.com/toandaominh1997/EfficientDet.Pytorch/commit/8a9ec2fc6db41ef3f14874703b3941acd4bd0244#diff-93102682735f61ab7d6b87aa1465caa4R38
eval.py script runs for me now. However, I see near zero performance with the provided weights. @dvlshah did you try running the eval.py script? If yes, what results are you seeing?