bilalsal Goto Github PK

antialiased-cnns

pip install antialiased-cnns to improve stability and accuracy

arrayexplorer

Eclipse Array Explorer

blocks

A Juptyer notebook on visualizing classification structure of large-scale classifiers

bstld

Sample scripts for the Bosch Small Traffic Lights Dataset

captum

Model interpretability and understanding for PyTorch

checklist

Beyond Accuracy: Behavioral Testing of NLP models with CheckList

cnn-mind-gap.github.io

visualization of CNN padding strategies

deeplearningexamples

Deep Learning Examples

drn

Dilated Residual Networks

eclipsetracer

facial-recognition-vgg-face

Code for facial recognition using the VGG Face Model

fbtt-embedding

This is a Tensor Train based compression library to compress sparse embedding tables used in large-scale machine learning models such as recommendation and natural language processing. We showed this library can reduce the total model size by up to 100x in Facebook’s open sourced DLRM model while achieving same model quality. Our implementation is faster than the state-of-the-art implementations. Existing the state-of-the-art library also decompresses the whole embedding tables on the fly therefore they do not provide memory reduction during runtime of the training. Our library decompresses only the requested rows therefore can provide 10,000 times memory footprint reduction per embedding table. The library also includes a software cache to store a portion of the entries in the table in decompressed format for faster lookup and process.

fcn.berkeleyvision.org

Fully Convolutional Networks for Semantic Segmentation by Jonathan Long*, Evan Shelhamer*, and Trevor Darrell. CVPR 2015 and PAMI 2016.

ieeevis.org

Website for ieeevis.org

models

Models and examples built with TensorFlow

places365

The Places365-CNNs for Scene Classification

pytorch-grad-cam

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

ssd_tensorflow_traffic_sign_detection

Implementation of Single Shot MultiBox Detector in TensorFlow, to detect and classify traffic signs

transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

tutorials

PyTorch tutorials.

vitpose_pytorch

An unofficial implementation of ViTPose [Y. Xu et al., 2022]