Finetuning Tutorial Missing Steps

Hi there,

The Torchvision Object Detection Tutorial discusses two paths, using Resnet50 or MobileNetV2. I tried copying the mobilnet code to replace the Resnet50 backbone and the image. Could someone either show me here or provide the updated colab notebook with the mobile net model working for the Fudan dataset fine-tuning?


TypeError Traceback (most recent call last)
in ()
7 )
8 # For Training
----> 9 images,targets = next(iter(data_loader))
10 images = list(image for image in images)
11 targets = [{k: v for k, v in t.items()} for t in targets]

3 frames
/usr/local/lib/python3.7/dist-packages/torch/ in reraise(self)
432 # instantiate since we don’t know how to
433 raise RuntimeError(msg) from None
→ 434 raise exception

TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File “/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/”, line 287, in _worker_loop
data = fetcher.fetch(index)
File “/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/”, line 49, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File “/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/”, line 49, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File “”, line 67, in getitem
img, target = self.transforms(img, target)
File “/content/”, line 23, in call
image, target = t(image, target)
File “/usr/local/lib/python3.7/dist-packages/torch/nn/modules/”, line 1102, in _call_impl
return forward_call(*input, **kwargs)
TypeError: forward() takes 2 positional arguments but 3 were given