RuntimeError: "sigmoid_cpu" not implemented for 'Half', when run command 'python grounding_dino_demo.py'

[loubron23]

(sam) loubron@loubron-PC:~/disk/sam/Grounded-Segment-Anything$ python grounding_dino_demo.py
UserWarning: Failed to load image Python extension: libc10_hip.so: cannot open shared object file: No such file or directory
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:3190.)
final text_encoder_type: bert-base-uncased
Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertModel: ['cls.seq_relationship.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.bias']

• This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
• This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
  FutureWarning: The device argument is deprecated and will be removed in v5 of Transformers.
  UserWarning: None of the inputs have requires_grad=True. Gradients will be None
  Traceback (most recent call last):
  File "grounding_dino_demo.py", line 21, in
  boxes, logits, phrases = predict(
  File "/home/loubron/disk/Grounded-Segment-Anything-main/GroundingDINO/groundingdino/util/inference.py", line 69, in predict
  prediction_logits = outputs["pred_logits"].cpu().sigmoid()[0] # prediction_logits.shape = (nq, 256)
  RuntimeError: "sigmoid_cpu" not implemented for 'Half'

[live-github]

Use cuda or remove
# if FP16_INFERENCE
# image = image.half()
# model = model.half()
in the grounding_dino_demo.py

[JCBreath]

Use cuda or remove # if FP16_INFERENCE # image = image.half() # model = model.half() in the grounding_dino_demo.py

Works perfectly, thanks!

[rexainn]

Use cuda or remove # if FP16_INFERENCE # image = image.half() # model = model.half() in the grounding_dino_demo.py

I'm sorry but I want to know how to use cuda for this script? I can use cuda for anything else, I think cuda will also work well for this project, but it's not. Should I need some extra settings?