Transformer-MM-Explainability
clip-italian
Transformer-MM-Explainability | clip-italian | |
---|---|---|
3 | 1 | |
709 | 172 | |
- | 1.2% | |
0.0 | 2.0 | |
8 months ago | 12 months ago | |
Jupyter Notebook | Jupyter Notebook | |
MIT License | - |
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.
Transformer-MM-Explainability
clip-italian
-
[N][P] We built the Italian CLIP 🇮🇹
The demo and paper links are coming out soon! Github: https://github.com/clip-italian/clip-italian Twitter: https://twitter.com/peppeatta/status/1419593282682773507
What are some alternatives?
pytorch-grad-cam - Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Basic-UI-for-GPT-J-6B-with-low-vram - A repository to run gpt-j-6b on low vram machines (4.2 gb minimum vram for 2000 token context, 3.5 gb for 1000 token context). Model loading takes 12gb free ram.
TorchDrift - Drift Detection for your PyTorch Models
clip-retrieval - Easily compute clip embeddings and build a clip retrieval system with them
explainerdashboard - Quickly build Explainable AI dashboards that show the inner workings of so-called "blackbox" machine learning models.
TargetCLIP - [ECCV 2022] Official PyTorch implementation of the paper Image-Based CLIP-Guided Essence Transfer.
shap - A game theoretic approach to explain the output of any machine learning model.
browser-ml-inference - Edge Inference in Browser with Transformer NLP model
pytea - PyTea: PyTorch Tensor shape error analyzer
WeightWatcher - The WeightWatcher tool for predicting the accuracy of Deep Neural Networks
cleverhans - An adversarial example library for constructing attacks, building defenses, and benchmarking both
univec - Multilingual CLIP