Masatoshi Abe

Thanks for publishing a great blog and implementation! I understand that the following implementation will create a new feature for train data. ```python from knnFeat import knnExtract newX = knnExtract(X,...

[FEATURE] Support variable input size of maxvit and coatnet

1

Will it be possible in the future to support variable input sizes for maxvit and coatnet? I am experimenting with adapting various models of timm to self-supervised learning such as...

No module named 'dinov2

2

I was having trouble running dinov2 after running I would appreciate it if you could let me know if there is a solution ``` (dinov2) abe@ganesa:~/kuma-ssl/dinov2$ python dinov2/run/train/train.py --nodes 1...

I performed self-supervised training of DINO on a pathology image dataset and analysed PCA as well as DINO-vit-feature. At the same time, I also analysed the PCA in the model...

I create new conda env and then ``` pip install -r requirements.txt pip install git+https://github.com/shumingma/fairseq.git@moe pip install -v -U git+https://github.com/facebookresearch/[email protected]#egg=xformers ``` installed above. however,I cant try using longvit ``` #https://github.com/microsoft/torchscale/blob/main/examples/longvit/longvit.py...

how to predict time by using AFT model?

1

Is it possible to predict survival times directly, as in the following torchlife code? ``` from torchlife.model import ModelAFT model = ModelAFT('Gumbel') model.fit(df) surv_prob = model.predict(df) mode_time = model.predict_time(df) ```