Anurag Arnab's repositories
adversarial-attacks
Code for our CVPR 2018 paper, "On the Robustness of Semantic Segmentation Models to Adversarial Attacks"
caffe-fold-batchnorm
Folds batch normalisation and the following scale layer into a single scale layer for networks trained in Caffe. This can be done at inference time to reduce memory consumption.
dynamically-instantiated-network
Pixelwise Instance Segmentation with a Dynamically Instantiated Network (CVPR 2017)
Volume-Renderer
Creates a 3D volume from a number of 2D image slices. This rotatable model is useful for visualizing CT scans and other medical imaging
Beat-Dropper-5000
A drum machine prototype created with the STM32F4 discovery microcontroller
Deep-Learning-Papers-Reading-Roadmap
Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!
kinetics-i3d
Convolutional neural network model for video classification trained on the Kinetics dataset.
oxford-machine-learning-2015
My solutions to the Oxford Computer Science Machine Learning 2015 course, found at https://github.com/oxford-cs-ml-2015
cs228-notes
Course notes for CS228: Probabilistic Graphical Models.
detectron2
Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks.
GALD-DGCNet
Source code and models of GALD net :tada:
glove.torch
glove wrapper for torch7
jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
mx-maskrcnn
An MXNet implementation of Mask R-CNN
pytorchvideo
A deep learning library for video understanding research.
SlowFast
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
Temporal-3D-Pose-Kinetics
Exploiting temporal context for 3D human pose estimation in the wild: 3D poses for the Kinetics dataset
torch-demos
Demos and tutorials around Torch7.