Update coco_utils.py

[vfdev-5]

Description:

• Fixing convert_to_coco_api as target["image_id"] should be an integer than tensor.

We get the following error:

  File "/tutorials/intermediate_source/tv-training-code.py", line 225, in main
    evaluate(model, data_loader_test, device=device)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/tutorials/intermediate_source/engine.py", line 102, in evaluate
    coco_evaluator.update(res)
  File "/tutorials/intermediate_source/coco_eval.py", line 37, in update
    coco_dt = COCO.loadRes(self.coco_gt, results) if results else COCO()
  File "/usr/local/lib/python3.10/dist-packages/pycocotools/coco.py", line 327, in loadRes
    assert set(annsImgIds) == (set(annsImgIds) & set(self.getImgIds())), \
AssertionError: Results do not correspond to current coco set

This happends because ground truth image_ids created by convert_to_coco_api are int but image_ids given by predictions are tensors.

Context:

• ref detection code is supposed to work on non-COCO datasets like in https://pytorch.org/tutorials/intermediate/torchvision_tutorial.html

For non-COCO datasets we are passing into the last branch (return convert_to_coco_api(dataset)) here:

vision/references/detection/coco_utils.py

Lines 174 to 183 in 37081ee

	def get_coco_api_from_dataset(dataset):
	# FIXME: This is... awful?
	for _ in range(10):
	if isinstance(dataset, torchvision.datasets.CocoDetection):
	break
	if isinstance(dataset, torch.utils.data.Subset):
	dataset = dataset.dataset
	if isinstance(dataset, torchvision.datasets.CocoDetection):
	return dataset.coco
	return convert_to_coco_api(dataset)

So, there is no impact for the current MSCOCO training script.

• Related PR : Add --backend and --use-v2 support to detection refs #7732, bb3aae7#r125193500

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/vision/7869

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❌ 32 New Failures, 1 Unrelated Failure

As of commit e367139 with merge base 5c1e62f ():

NEW FAILURES - The following jobs have failed:

• build / linux-job (gh)
• c-source / linux-job (gh)
• linux (linux.12xlarge, cpu) / linux-job (gh)
• linux (linux.g5.4xlarge.nvidia.gpu, cuda, 11.8) / linux-job (gh)
• macos (macos-12) / macos-job (gh)
• macos (macos-m1-12) / macos-job (gh)
• onnx / linux-job (gh)
• python-source-and-configs / linux-job (gh)
• python-types / linux-job (gh)
• unittests-extended / linux-job (gh)
• unittests-linux (3.10, linux.12xlarge, cpu) / linux-job (gh)
• unittests-linux (3.11, linux.12xlarge, cpu) / linux-job (gh)
• unittests-linux (3.8, linux.12xlarge, cpu) / linux-job (gh)
• unittests-linux (3.8, linux.g5.4xlarge.nvidia.gpu, cuda, 11.8) / linux-job (gh)
• unittests-linux (3.9, linux.12xlarge, cpu) / linux-job (gh)
• unittests-macos (3.10, macos-12) / macos-job (gh)
• unittests-macos (3.11, macos-12) / macos-job (gh)
• unittests-macos (3.8, macos-12) / macos-job (gh)
• unittests-macos (3.8, macos-m1-12) / macos-job (gh)
• unittests-macos (3.9, macos-12) / macos-job (gh)
• unittests-prototype (3.10, linux.12xlarge, cpu) / linux-job (gh)
• unittests-prototype (3.11, linux.12xlarge, cpu) / linux-job (gh)
• unittests-prototype (3.8, linux.12xlarge, cpu) / linux-job (gh)
• unittests-prototype (3.8, linux.g5.4xlarge.nvidia.gpu, cuda, 11.8) / linux-job (gh)
• unittests-prototype (3.9, linux.12xlarge, cpu) / linux-job (gh)
• unittests-windows (3.10, windows.4xlarge, cpu) / windows-job (gh)
• unittests-windows (3.11, windows.4xlarge, cpu) / windows-job (gh)
• unittests-windows (3.8, windows.4xlarge, cpu) / windows-job (gh)
• unittests-windows (3.8, windows.g5.4xlarge.nvidia.gpu, cuda, 11.8) / windows-job (gh)
• unittests-windows (3.9, windows.4xlarge, cpu) / windows-job (gh)
• windows (windows.4xlarge, cpu) / windows-job (gh)
• windows (windows.g5.4xlarge.nvidia.gpu, cuda, 11.8) / windows-job (gh)

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• pytorch/vision / wheel-py3_8-cpu-aarch64 (gh)

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[NicolasHug]

Thanks @vfdev-5

[github-actions]

Hey @NicolasHug!

You merged this PR, but no labels were added. The list of valid labels is available at https://github.com/pytorch/vision/blob/main/.github/process_commit.py