Comments (2)
Hi @betterze, thanks for your kind words and for your interest in our work!
Let me try to clarify, but if my answer isn't good enough please let me know:
let's take the ViT example because it's simpler.
If we look at the ViT_new.py code, we can see the lines that are responsible for saving the gradients and attention maps:
self.save_attention_map(attn) attn.register_hook(self.save_attn_gradients)
If you notice, the first thing we do in the ViT notebook's generate_relevance
function is to run a forward pass with the example we wish to explain:
output = model(input, register_hook=True)
, this triggers the "forward hook " that we set in this line: self.save_attention_map(attn)
, i.e. for each self-attention block this forward pass saves the self-attention matrix in self.attention_map
.
After this forward pass, each attention block stores its attention map in self.attention_map
.
Moving to the gradients, this line: attn.register_hook(self.save_attn_gradients)
registers a backward hook on the attn tensor, such that when we backpropagate the gradients, the hook will be called for the attention map. This hook saves the attention-map's gradient in self.attn_gradients
. The backward pass is also triggered from the generate_relevance
function in the ViT notebook in line: one_hot.backward(retain_graph=True)
.
After this step, we have both gradients and attention maps saved in each self-attention block. All we need to do is iterate over the blocks and apply the rules on the maps + gradients, as you mentioned:
grad = blk.attn.get_attn_gradients() cam = blk.attn.get_attention_map()
I really hope this helps, but if somehow I failed to answer your question, please let me know and I'll clarify as needed.
Thanks :)
from transformer-mm-explainability.
Dear Hila,
Thank you very much for your detail answer. It is really helpful.
After a few experiments, I believe I understand it now.
Thank you again for your help, I really appreciate it.
Best Wishes,
Alex
from transformer-mm-explainability.
Related Issues (20)
- Questions about CLIP visualization. HOT 4
- Batching for CLIP Explainability HOT 2
- Questions about the Relavance Matrix HOT 2
- Generate relevance matrix in ViT of Hugging Face HOT 2
- How can I choose the method when I run the script ? HOT 2
- The data set downloaded automatically is too large HOT 1
- In 6.2 LXMERT, report an error"requests.exceptions.MissingSchema: Invalid URL 'val2014COCO_val2014_000000092107.jpg': No schema supplied. " HOT 1
- Details about the changes in the code of base models HOT 1
- Question about the visualization of CLIP‘s text token HOT 2
- Object detection/Segmentation Explainability HOT 1
- Problems with running it in Google colab HOT 2
- Using the methods for a custom architecture HOT 4
- ImportError: No module named lxmert.lxmert.src.tasks HOT 2
- Question about the CLIP Demo HOT 1
- Application to Sparse/Low-Rank Attention Matrices HOT 1
- Use non hacked models HOT 1
- Checking how well this works with Segment Anything? HOT 1
- Is this really using the technique from the publication? HOT 1
- self.attn_probs in ResidualAttentionBlock() causes problems - how to make explainability work with mlfoundations / open_clip model
- when trying to use the colab notebook for RN50 im getting AttributeError: 'ModifiedResNet' object has no attribute 'transformer'
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from transformer-mm-explainability.