Tim Meinhardt
Does this error occur immediately or after a few iterations? The former would be very strange indeed. I think this is related to your input data. You should debug the...
If it works for our CrowdHuman/MOT you have to figure out what the difference to your custom dataset is. You said the `boxes` in `assert (boxes1[:, 2:] >= boxes1[:, :2]).all()`...
But you said NaNs appear even if you set all the learning rates to zero? This would be contradictive to the query embeddings becoming zero. Double check if this still...
How do the loss values develop until the network produces NaN output values? If for example the bounding box loss goes up there might be something wrong with that.
Our code logs loss values in the command line or via Visdom. You should use these outputs to debug your results. But yes, that overall loss doesnt look pathological.
You could set `vis_and_log_interval=1` to see results after each iteration.
Maybe there is something to be seen in the Visdom logging of the network outputs? Have you tried deactivating all data augmentations?
I am sorry but we never trained smaller models than the provided ResNet50.
After downloading and unpacking the COCO dataset into the `data` directory you should be able to train a model on COCO detection by running something like this: ``` python src/train.py...
Indeed models trained with deformable Transformers currently do not support the generation of attention maps. I added an assert statement and opened an issue https://github.com/fundamentalvision/Deformable-DETR/issues/80 as this is not even...