search

facebookresearch / sam2

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Apache License 2.0
12.19k stars 1.11k forks source link

error with shape size #44

Open wangmiaowei opened 3 months ago

wangmiaowei commented 3 months ago

I found the shape size can also cause bug, when my input is with the size image: (3006, 4013, 3).

I get error like: RuntimeError: nonzero is not supported for tensors with more than INT_MAX elements, file a support request: the full list:

warnings.warn( Traceback (most recent call last): File "/home/wmw/project/codespace/segment-anything-2-main/test.py", line 44, in masks = mask_generator.generate(image) File "/home/wmw/miniconda3/envs/gspl/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "/home/wmw/project/codespace/segment-anything-2-main/sam2/automatic_mask_generator.py", line 178, in generate mask_data = self._generate_masks(image) File "/home/wmw/project/codespace/segment-anything-2-main/sam2/automatic_mask_generator.py", line 215, in _generate_masks crop_data = self._process_crop(image, crop_box, layer_idx, orig_size) File "/home/wmw/project/codespace/segment-anything-2-main/sam2/automatic_mask_generator.py", line 253, in _process_crop batch_data = self._process_batch( File "/home/wmw/project/codespace/segment-anything-2-main/sam2/automatic_mask_generator.py", line 361, in _process_batch data["rles"] = mask_to_rle_pytorch(data["masks"]) File "/home/wmw/project/codespace/segment-anything-2-main/sam2/utils/amg.py", line 120, in mask_to_rle_pytorch change_indices = diff.nonzero() RuntimeError: nonzero is not supported for tensors with more than INT_MAX elements, file a support request

bhack commented 3 months ago

It seems really related to https://github.com/pytorch/pytorch/pull/125850

wangmiaowei commented 3 months ago

yeas, so no solution currently?

heyoeyo commented 3 months ago

The same problem occurred on SAM v1 and someone posted a change to the code that fixed it: https://github.com/facebookresearch/segment-anything/pull/569

I assume something similar would work with v2. Alternatively, I believe running on CPU also avoids the problem.

bhack commented 3 months ago

Yes with that workaround it will work but it is going to be slower as you need to process it in chunks. It is an upstream CUDA/CUB limit as pytorch nonzero is implemented on Nvidia GPU using CUB primitives. It seems that Nvidia it is still lagging to fix it as you can see from the upstream ticket: https://github.com/NVIDIA/cccl/issues/1422