UNI
UNI copied to clipboard
Towards a general-purpose foundation model for computational pathology - Nature Medicine
Dear authors, would it be possible for you to share the pretrained (on UNI features) ABMIL model used in your experiments? Thanks for your work!
hello,nice work,when can I get the permission for the pretrained weights in huggingface,thanks
Dear authors, I ran the [walkthrough notebook](https://github.com/mahmoodlab/UNI/blob/main/notebooks/uni_walkthrough.ipynb), and the model was downloaded twice (see screenshot). 1. I get the symbolic link `assets/ckpts/vit_large_patch16_224.dinov2.uni_mass100k/pytorch_model.bin` pointing to a file in `.cache/huggingface/hub/models--MahmoodLab--UNI/`. 2. The...
Hello, Are you planning to release the trained model on SegPath data so that we can directly run inference on our samples?
Hello, I was wondering if you could provide additional details on the evolution of loss functions during the pre-training of UNI. [It has indeed been observed ](https://github.com/facebookresearch/dinov2/issues/143)that instabilities or convergence...
Hello, thank you very much for your contribution. In your paper, you mentioned using the UNI pre-trained encoder to extract features from histopathology ROI, and also provided sample code. What...
May I ask if you could provide the code for the tasks of ROI retrieval? Thank you for your great work!
Hello authors, Thank you for you amazing work. Can you publish the config of CLAM for extracting HunCRC data ? I can't extract, even with very low thresholds. `{'seg_params': {'seg_level':...
Dear authors, `faiss` is unnecessary for using the UNI model unless someone wants to use `uni/downstream/eval_patch_features/protonet.py` and the corresponding part of the walkthrough notebook. I added the link to the...
I used something similar to [this](https://github.com/huggingface/pytorch-image-models/discussions/1232) to extract the attention scores for the penultimate layer, as explained in the caption for figure 3e. However, I found that the attention maps...