PyTorch-Model-Compare
PyTorch-Model-Compare copied to clipboard
AntixK
Compare neural networks by their feature similarity
Thanks for this great little module! I was able to adapt the code to deal with models suitable for speech recognition (mostly transformers and conformers) and I'm learning a lot...
When I was trying to compare the same model trained on different datasets, I encountered a weird problem: It works fine when I compare all layers: `cka = CKA(model1, model2,...
I tried comparing many EfficientNet to other models (and its variants), but all I got is this error: ```AssertionError: HSIC computation resulted in NANs```. One example: ``` python3 eff_b0b2_compare.py ```...
I tried to compare Resnet50 vs ViT but got this error ValueError: Input image size (32*32) doesn't match model (224*224). The code I used is model1 = resnet50(pretrained=False) layers_Res1 =...
Thanks for sharing the code. I see that the models in the examples in this repo are all for classification. I was wondering if we can compare two models that...
It looks like there's a subtle bug on this line: https://github.com/AntixK/PyTorch-Model-Compare/blob/main/torch_cka/cka.py#L156 ``` num_batches = min(len(dataloader1), len(dataloader1)) ``` `len(dataloader1)` is in there twice, I assume it's supposed to be ``` num_batches...
!pip install transformers import torch from torchvision import transforms from torch.utils.data import Dataset, DataLoader import torch.nn as nn import torch.nn.functional as F from transformers import ViTFeatureExtractor, ViTModel, ViTConfig, AutoConfig #...
Can you add an example to compare two datasets for a single model.
Hi, Thanks for the clean repo. I ran a sanity check with giving the exact replica of the same model, expecting to get an identity diagonal for the output of...
did anyone solve the issue with "HSIC computation resulted in NANs"? Any suggestions how to address it would be helpful. Thank you.
