pytorch-grad-cam
deit
pytorch-grad-cam | deit | |
---|---|---|
5 | 2 | |
9,456 | 3,822 | |
- | - | |
5.4 | 5.1 | |
about 2 months ago | about 2 months ago | |
Python | Python | |
MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
pytorch-grad-cam
-
Exploring GradCam and More with FiftyOne
For the two examples we will be looking at, we will be using pytorch_grad_cam, an incredible open source package that makes working with GradCam very easy. There are excellent other tutorials to check out on the repo as well.
-
Which layers are doing image segmentation on AutoEncoders/U-NET?
https://github.com/jacobgil/pytorch-grad-cam.
-
[D] Algorithm for view prediction?
I know I would like to use grad-CAM https://github.com/jacobgil/pytorch-grad-cam
-
[P] Adapting Class Activation Maps for Object Detection and Semantic Segmentation
https://github.com/jacobgil/pytorch-grad-cam is a project that has a comprehensive collection of Pixel Attribution Methods for PyTorch (like the package name grad-cam that was the original algorithm implemented).
- [Project] Recent Class Activation Map Methods for CNNs and Vision Transformers
deit
-
Exploring GradCam and More with FiftyOne
We can now apply the transform and try ourselves with a vision transformer. We will use DeiT from the FiftyOne model zoo. It can be loaded with a pre and postprocessor like the following:
-
[D] What are the strongest plain baselines for Vision Transformers on ImageNet?
I think Deit III is pretty sota
What are some alternatives?
Transformer-Explainability - [CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
pytorch-lightning - Build high-performance AI models with PyTorch Lightning (organized PyTorch). Deploy models with Lightning Apps (organized Python to build end-to-end ML systems). [Moved to: https://github.com/Lightning-AI/lightning]
pytorch-CycleGAN-and-pix2pix - Image-to-Image Translation in PyTorch
tf-keras-vis - Neural network visualization toolkit for tf.keras
Transformer-MM-Explainability - [ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.
pytorch-tutorial - PyTorch Tutorial for Deep Learning Researchers
Real-Time-Voice-Cloning - Clone a voice in 5 seconds to generate arbitrary speech in real-time
EasyOCR - Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
pytorch-lightning - Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.
XAI - Genetic programming method for explaining complex black-box models
dino-vit-features - Official implementation for the paper "Deep ViT Features as Dense Visual Descriptors".
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.