While running grounded_sam2_local_demo.py facing following warning

[Jaykumaran]

`UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3609.)
final text_encoder_type: bert-base-uncased

UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at ../torch/csrc/utils/tensor_numpy.cpp:206.)

UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.

UserWarning: None of the inputs have requires_grad=True. Gradients will be None
(sam2) opencvuniv@opencvuniv:~/.../Grounded-SAM2/Grounded-SAM-2$ python grounded_sam2_local_demo.py --user_reentrant=False
UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3609.)
final text_encoder_type: bert-base-uncased

UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at ../torch/csrc/utils/tensor_numpy.cpp:206.)

UserWarning: torch.utils.checkpoint: the use_reentrant parameter should be passed explicitly. In version 2.4 we will raise an exception if use_reentrant is not passed. use_reentrant=False is recommended, but if you need to preserve the current default behavior, you can pass use_reentrant=True. Refer to docs for more details on the differences between the two variants.

UserWarning: None of the inputs have requires_grad=True. Gradients will be None
`

[rentainhe]

Hi @Jaykumaran Would you like to share more info about your error, UserWarning is not bug I think

[siberianspot]

It’s a bug in groundingdino.utils.inference.load_image() function. To fix it, append to PIL.Image open part a copy() method call, something like this:

# image_source = Image.open(image_path).convert("RGB")
image_source = Image.open(image_path).copy().convert("RGB")