Prabhat Singh

> to execute the models in GPU add `.to(device = 'cuda')` at the end of GroundingDINO and SAM model. > > If the execution consumes a lot of ram try...

> @jasonborn0 You have to make sure your `GroundingDINO` is installed with a GPU instead of CPU. The groundingdino._C isn't installed without GPU. And the default hyperparameter is `--device "cuda"`,...

> You should set `CUDA_HOME` before installing the repo~ here is an example > > ```shell > export CUDA_HOME=/path/to/cuda-11.3/ > pip install ... > ``` Simply setting up CUDA HOME,...

Can you check if there's any file with name similar to this `groundingdino/_C.cpython-310-x86_64-linux-gnu.so` basically starting with _C , in setup.py this particular extension is build as seen here ` ext_modules...

``` /home/lcc/github.com/Grounded-Segment-Anything/GroundingDINO/groundingdino/models/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!") ``` I am assuming you...

Try to use a virtual environment , such as [pipenv](https://pypi.org/project/pipenv/) , and install all the packages in this environment using pip , also if I assume you are using torch...

I will list down the steps I followed ,from scratch . I tried running the [notebook](https://github.com/IDEA-Research/Grounded-Segment-Anything/blob/main/grounded_sam.ipynb) . Step 1- Setup Venv in this directory by using `pipenv` . Step 2...

Can you try to run the same script by giving device argument as `cpu` and check if it's running properly or not?

Your pytorch supports version 11.7, mostly you have latest pytorch version, try to install cuda toolkit version 11.7 here's the [link](https://developer.nvidia.com/cuda-11-7-1-download-archive) for the same

> May I use the torch-2.0.0+cu118 as the CUDA_HOME?It is include cuda toolkit 118? When you build custom cuda extension that is `_C` file , it uses local cuda toolkit,...