ramonhollands

I've got the same issue. Also on the spotify app on my macbook air.

I got the same error and discovered that the problem in my case was caused because of different image formats mingled. By default, the Yolo dataloader takes only the '.jpg'...

Thanks for your fast reply. It looks like it's training correctly after changing the fp16 setting to false again. Could that be the cause? First 30 epochs have succeeded so...

It's a RTX3090, running CUDA 11.4. I am doing some experiments these days and let you know. If you are interested in this dataset, I can share it with you....

@glenn-jocher Might be interesting to do a final step by unfreezing and training the complete netwerk again with differentiated learning rate. So complete training process would be (default method in...

Ill take that challenge the coming weeks. Trying to wrap your amazing work in the fast.ai framework to be able to use best of both worlds, including the fastai learning...

You have to split the backbone and head parameters and add additional param groups for both with different 'lr' argument (https://pytorch.org/docs/stable/optim.html). I wrote some initial code which Ill post later...

See https://github.com/ramonhollands/different_learning_rates/blob/master/train.py I have added two parameters to experiment with: - freeze-backone (which freezes backbone on start and unfreezes after 4 epoch - diff-backbone (which lowers the learning rate for...

Thanks for your reply. I'm using the latest tensorflow version ([2.16.1](https://mvnrepository.com/artifact/org.tensorflow/tensorflow-lite/2.16.1)) The GPU delegate looks correctly configured because it works on one model and I'm using the exact same configuration...

@sushreebarsa, just to be sure, I am tagging your name. Thanks in advance for your response.