Open gasharper opened 11 months ago
Thank you for your interest. The official code will be released within a month. Here is an unrefined version of the code for your reference: code, model
step1 train an existing "froen CLIP" network, e.g., FreeSeg:
python train_net.py --config-file configs/coco-stuff-164k-156/mask2former_zss.yaml --num-gpus 4
step2 Fine-tune CLIP Image Encoder with MAFT:
python train_net.py --config-file configs/coco-stuff-164k-156/mask2former_ft.yaml --num-gpus 4
python train_net.py --config-file configs/coco-stuff-164k-156/eval.yaml --num-gpus 8 --eval-only MODEL.WEIGHTS path/to/your/weights
I wonder where the IP-CLIP Encoder is, there is only one myclip_model
in ft.py, and its structure is "ViT-B/16"
like normal CLIP.
Thank you!
A new version of the code has been released. The implementation of IPCLIP is at here.
Thank you, that is very great work!
@jiaosiyu1999 Hi, it seems that the code is based on detectron2 and the third-party operator (MSDeformAttnFunction), it is not friendly for beginners to deploy. Is it possible to provide a single image inference demo only based on some necessary libraries (like Pytorch, OpenCV, etc.)? It may greatly help us to get the main ideas of the whole work. Thanks for your early reply.
thanks for your impressive work! I wondering when are the code and pre-trained model will be released. Thank you!