Open chrisrapson opened 11 months ago
Your own custom data is also human pose data and num_keypoints is 17, as same order as coco keypoints?
My custom dataset was different, but as I said, I saw this strange behaviour even when training on a subset of the COCO dataset.
Anyway, it's a long time ago now. I managed to train a ViTPose network which had reasonable accuracy, but it turned out that other architectures were better for our use case.
Has anybody else had problems training on a small dataset? I've got one with 60 images in the training set, 10 in the validation set. It gives consistently 0 or -1 for all of the validation results.
I've tried:
pretrained=None
In all epochs, the results look like:
or
It looks like ViTPose would usually report training results after 50 batches, but with a dataset this small, there are less than 50 batches per epoch.
Training on the full COCO dataset seems to be running fine. Starting from scratch, the
acc_pose
slowly increases from ~0.02 to ~0.3 over the first two epochs. Loss shrinks from 0.0022 to 0.0017.