GroundingDINO
GroundingDINO copied to clipboard
Error while demo
I installed and passed every installition steps without any error but i get this error below
/GroundingDINO/ms_deform_attn.py:31: UserWarning: Failed to load custom C++ ops. Running on CPU mode Only!
warnings.warn("Failed to load custom C++ ops. Running on CPU mode Only!")
/home/metehan/.pyenv/versions/3.8.12/envs/dino_deneme/lib/python3.8/site-packages/torch/functional.py:568: 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:2228.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
final text_encoder_type: bert-base-uncased
_IncompatibleKeys(missing_keys=[], unexpected_keys=['label_enc.weight', 'bert.embeddings.position_ids'])
Traceback (most recent call last):
File "demo/inference_on_a_image.py", line 202, in
also with python demo script which is provided, i get this error
Exception has occurred: NameError
name '_C' is not defined
File "/home/metehan/dino_deneme/GroundingDINO/groundingdino/models/GroundingDINO/ms_deform_attn.py", line 53, in forward
output = _C.ms_deform_attn_forward(
File "/home/metehan/dino_deneme/GroundingDINO/groundingdino/models/GroundingDINO/ms_deform_attn.py", line 338, in forward
output = MultiScaleDeformableAttnFunction.apply(
File "/home/metehan/dino_deneme/GroundingDINO/groundingdino/models/GroundingDINO/transformer.py", line 785, in forward
src2 = self.self_attn(
File "/home/metehan/dino_deneme/GroundingDINO/groundingdino/models/GroundingDINO/transformer.py", line 576, in forward
output = checkpoint.checkpoint(
File "/home/metehan/dino_deneme/GroundingDINO/groundingdino/models/GroundingDINO/transformer.py", line 258, in forward
memory, memory_text = self.encoder(
File "/home/metehan/dino_deneme/GroundingDINO/groundingdino/models/GroundingDINO/groundingdino.py", line 327, in forward
hs, reference, hs_enc, ref_enc, init_box_proposal = self.transformer(
File "/home/metehan/dino_deneme/GroundingDINO/groundingdino/util/inference.py", line 68, in predict
outputs = model(image[None], captions=[caption])
File "/home/metehan/dino_deneme/GroundingDINO/inder.py", line 12, in
Seeing the same issue here. Installed per the VRB repo (https://github.com/shikharbahl/vrb).
Edit: Seems this issue is common. Will see the other posts and check back.