Deep Learning

An implementation of Global Self-Attention Network, which proposes an all-attention vision backbone that achieves better results than convolutions with less parameters and compute.

This is the Pytorch implementation for Apollo: An Adaptive Parameter-wise Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization

1st Place Solutions of 3D AI Challenge 2020(IJCAI-PRICAI 2020 Workshop) - Instance Segmentation Track

Generalized Minimal Distortion Principle for Blind Source Separation

The problem is to estimate the growth stage of a wheat crop based on an image sent in by the farmer. Model must take in an image and output a prediction for the growth stage of the wheat shown, on a scale from 1 (crop just showing

1st place solution for the Kaggle PANDA Challenge

[Neurips'20] Self-supervised Co-Training for Video Representation Learning. Tengda Han, Weidi Xie, Andrew Zisserman.

[ICML'20] Multi Steepest Descent (MSD) for robustness against the union of multiple perturbation models.

Pytorch code for the arXiv paper "Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition"

Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true class with high probability.

All Word Embeddings from One Embedding

code for "OcCo: Occlusion Completion for Point Cloud Pre-Training"

An example of time series augmentation methods with Keras

The implementation of FDCNN in paper - A Feature Difference Convolutional Neural Network-Based Change Detection Method

A third-party Tensorflow Implementation for paper "BlazePose: On-device Real-time Body Pose tracking".

This project provides a paper list about pedestrian detection following the taxonomy in our survey paper. Single-spectral pedestrian detection and multispectral pedestrian detection are both summarized.

How to calibrate your neural network classifier: Getting accurate probabilities from a classification model

A list of papers and resources (data,code,etc) for holistic 3D reconstruction in computer vision

情感分析旨在自动识别和提取文本中的倾向、立场、评价、观点等主观信息。它包含各式各样的任务，比如句子级情感分类、评价对象级情感分类、观点抽取、情绪分类等

Industry-strength Computer Vision workflows with Keras

A Generative Adversarial Network implementation that generates Sharingans. This was trained on Google Colab with 3000 epochs and it took about 10 minutes to train.

This repository hosts the notebooks for the 2020 MONAI Bootcamp event. The data required for the notebooks is available through the download mechanisms given in each notebook or through the organizers. All bootcamp participants ca

To build a CNN model for detecting COVID-19 and create a complete end to end Project.

PyTorch implementation From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering

We are implementing differentiable models of robot manipulators, which allows us to learn typically assumed to be known models of robots for control and motion planning. These models can then be used in more complex reinforcement

📝Awesome and classical image retrieval papers

A persistent Google Colab notebook that lets you run a full GNU desktop.

Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation"

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

This repository provides Python codes and Jupyter Notebooks accompanying the Artificial Intelligence in Finance book published by O'Reilly.

An Instagram Bot serving as an account, people can use to create DeepFakes on Instagram.

a machine learning tool that allows to train, test and use models without writing code

Data structures & Algorithms are an essential part of programming. It comes under the fundamentals of computer science. It gives us the advantage of writing better and efficient code in less time. It is a key topic when it comes t