Skip to content

Adding a Colab Notebook for ease of use #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Adding a Colab Notebook for ease of use #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
311da9a
Explicit device placement
sayakpaul Apr 3, 2021
4f92628
added a colab notebook
sayakpaul Apr 3, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
325 changes: 325 additions & 0 deletions vit_explain.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

6 changes: 4 additions & 2 deletions vit_grad_rollout.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,8 @@
import numpy as np
import cv2

DEVICE = "cuda" if torch.cuda.is_available() else "cpu"

def grad_rollout(attentions, gradients, discard_ratio):
result = torch.eye(attentions[0].size(-1))
with torch.no_grad():
Expand Down Expand Up @@ -57,10 +59,10 @@ def get_attention_gradient(self, module, grad_input, grad_output):
def __call__(self, input_tensor, category_index):
self.model.zero_grad()
output = self.model(input_tensor)
category_mask = torch.zeros(output.size())
category_mask = torch.zeros(output.size()).to(DEVICE)
category_mask[:, category_index] = 1
loss = (output*category_mask).sum()
loss.backward()

return grad_rollout(self.attentions, self.attention_gradients,
self.discard_ratio)
self.discard_ratio)