Have you test your env installation? It has version conflict.

[Huangruopeng]

When I run cd ../YOLO-World pip install -e . I meet this problem. Traceback (most recent call last): File "<string>", line 2, in <module> File "<pip-setuptools-caller>", line 34, in <module> File "/tmp/pip-install-7ek3iu8e/mmcv_d71dfe9e702c484282385c89b9550300/setup.py", line 460, in <module> setup( File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/setuptools/__init__.py", line 87, in setup return distutils.core.setup(**attrs) File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/setuptools/_distutils/core.py", line 185, in setup return run_commands(dist) File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/setuptools/_distutils/core.py", line 201, in run_commands dist.run_commands() File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/setuptools/_distutils/dist.py", line 969, in run_commands self.run_command(cmd) File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/setuptools/dist.py", line 1208, in run_command super().run_command(command) File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/setuptools/_distutils/dist.py", line 988, in run_command cmd_obj.run() File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/wheel/bdist_wheel.py", line 299, in run self.run_command('build') File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/setuptools/_distutils/cmd.py", line 318, in run_command self.distribution.run_command(command) File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/setuptools/dist.py", line 1208, in run_command super().run_command(command) File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/setuptools/_distutils/dist.py", line 988, in run_command cmd_obj.run() File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/setuptools/_distutils/command/build.py", line 132, in run self.run_command(cmd_name) File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/setuptools/_distutils/cmd.py", line 318, in run_command self.distribution.run_command(command) File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/setuptools/dist.py", line 1208, in run_command super().run_command(command) File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/setuptools/_distutils/dist.py", line 988, in run_command cmd_obj.run() File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/setuptools/command/build_ext.py", line 84, in run _build_ext.run(self) File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/setuptools/_distutils/command/build_ext.py", line 346, in run self.build_extensions() File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/torch/utils/cpp_extension.py", line 611, in build_extensions _check_cuda_version(compiler_name, compiler_version) File "/home/rocair/anaconda3/envs/openyolo3d/lib/python3.10/site-packages/torch/utils/cpp_extension.py", line 479, in _check_cuda_version raise RuntimeError(CUDA_MISMATCH_MESSAGE.format(cuda_str_version, torch.version.cuda)) RuntimeError: The detected CUDA version (11.3) mismatches the version that was used to compile PyTorch (12.6). Please make sure to use the same CUDA versions. It shows pytorch version is 12.6 but your previous step is cd models/Mask3D/ pip3 install torch==1.12.1+cu113 torchvision==0.13.1+cu113 --extra-index-url https://download.pytorch.org/whl/cu113

I don't know have you test your installation step?

Thank you so much

[aminebdj]

Hi @Huangruopeng ,

Yes I tested the installation multiple times and it works well. After installing yoloworld you need to reinstall pytorch again in the steps that come after. Also, please Make sure your Cuda version is 11.x.

Best, Amine

[Huangruopeng]

Thank you for your reply. I found that the whole installation process updates cuda and torch version many times. maybe that is the problem. By the way, the datasset ScanNet200 preprocessed is too big, downloading always break. Could you share separated smaller dataset? Thank you so much!