Comments (2)
Thank you very much for the batch example in the colab! I am able to replicate your batching code on my end, and the heatmaps look similar to what I had before and generate a lot faster. Appreciate the help and response!
from transformer-mm-explainability.
Hi @Alacarter, thanks for your interest in our work!
I updated our colab notebook to demonstrate how batching can be done.
In our notebook, I used a single image with multiple texts. In order to create a "one-hot" vector, I duplicated the image batch_size
times and then created a "one-hot" vector for each pair of (image, text).
Similarly, if you have a batch of images and texts, simply create a one hot with the shape batch_zise x batch_size
and set it to be the identity matrix.
I hope this helps, please refer to our colab for all the details :)
Hila.
from transformer-mm-explainability.
Related Issues (20)
- 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'
- Applicability to decoder transformers with causal mask
- save_visual_results in visualBERT
- How to apply this work on google/vit model from hugging face ? HOT 1
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.