Daniel M. García-Ocaña

Hi, it works with CUDA 11.8. My current setup: - torch==2.0.1 - torchvision==0.15.2 ``` Cuda compilation tools, release 11.8, V11.8.89 Build cuda_11.8.r11.8/compiler.31833905_0 ``` gcc version 9.4.0 (Ubuntu 9.4.0-1ubuntu1~20.04.1)

Hi, I just added the following lines to my .bashrc file: ``` # >>> CUDA post-installation actions >>> export PATH=/usr/local/cuda/bin${PATH:+:${PATH}} export LD_LIBRARY_PATH=/usr/local/cuda/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}} #

Hi! I think that the problem is in your torch versions. Last, try the following: 1) install [these trird party libraries](https://docs.nvidia.com/cuda/archive/11.8.0/cuda-installation-guide-linux/index.html#install-libraries) (according to your OS, mine is Ubuntu) for CUDA...

Hi everyone, If you check this [demo notebook](https://colab.research.google.com/github/facebookresearch/segment-anything/blob/main/notebooks/predictor_example.ipynb#scrollTo=f6923b94), it is explained that the input mask is not such a mask: it is supposed to be the output low resolution mask...

@cip8 apologize if my response was not to your liking or not what you were looking for. I you had taken the time to deeply read the paper and replicate...

Same problem on my side, when converting RTMO to TRT and trying to perform inference with MMDeploy

The purpose of SAM model is to segment each object in an image. This repository is an improved version of original's [Meta SAM](https://github.com/facebookresearch/segment-anything). Check it for more info :smile: