ODISE
ODISE copied to clipboard
NVlabs
Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]
Hi, how can I get the confidence score of each instance segmentation in the demo.py?
Thanks for your great work. When I try to train the model with eight 3090 GPUs with the following commands, `./tools/train_net.py --config-file configs/Panoptic/odise_label_coco_50e.py --num-gpus 8 --amp --ref 32` The following...
running build_ext building 'MultiScaleDeformableAttention' extension Emitting ninja build file //ODISE/third_party/Mask2Former/build/temp.linux-x86_64-cpython-39/build.ninja... error: [Errno 2] No such file or directory: '//ODISE/third_party/Mask2Former/build/temp.linux-x86_64-cpython-39/build.ninja' [end of output] note: This error originates from a subprocess, and...
i follow your install.md step by step and one by one .but unfortunately i still confronted this problem when i run pip install -e . Failed to build mask2former ERROR:...
About 'K-Means Clustering of Frozen Diffusion Features', how do you perform on the dataset? Because the LDM model accept the text input to generate the new image samples, and what...
when run "pip install -e .", the error happen: lude/ATen/cuda/CUDAContext.h:6:10: fatal error: cusparse.h: No such file or directory #include ^~~~~~~~~~~~ compilation terminated. error: command '/home/cheng/ws/miniconda3/envs/odise/bin/nvcc' failed with exit code 1...
When I try to install these versions "conda install pytorch=1.13.1 torchvision=0.14.1 pytorch-cuda=11.6 -c pytorch -c nvidia", I got the following error. **"Downloading and Extracting Packages CondaError: Downloaded bytes did not...
CUDA out of memory. Tried to allocate 32.00 MiB (GPU 0; 23.69 GiB total capacity; 21.31 GiB already allocated; 12.06 MiB free; 21.46 GiB reserved in total by PyTorch) If...
Thanks for the excellent work in open source. The [run_on_image](https://github.com/NVlabs/ODISE/blob/2b187e4b2ff4c3d5da342aec2cc234b537720a65/demo/demo.py#L173) function says the input image should be in BGR order. But in the [demo code](https://github.com/NVlabs/ODISE/blob/2b187e4b2ff4c3d5da342aec2cc234b537720a65/demo/demo.py#L405), the input image is in...
