-
Mastercard
Starred repositories
A PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks"
code for "Fully Neural Network based Model for General Temporal Point Processes"
The fundamental package for scientific computing with Python.
Book in preparation: introduction to theoretical computer science
An end-to-end PyTorch framework for image and video classification
A curated list of image captioning and related area resources. :-)
📚 A collection of Deep Learning based Image Colorization and Video Colorization papers.
A curated list of awesome self-supervised methods
A PyTorch implementation of "Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks" (KDD 2019).
Official implementation of Character Region Awareness for Text Detection (CRAFT)
Datasets, Transforms and Models specific to Computer Vision
Tensors and Dynamic neural networks in Python with strong GPU acceleration
HDF5 for Python -- The h5py package is a Pythonic interface to the HDF5 binary data format.
A cutting-edge portfolio web page utilizing vanilla JavaScript.
A collection of infrastructure and tools for research in neural network interpretability.
Visualizing intermediate activation in Convolutional Neural Networks with Keras
Code and hyperparameters for the paper "Generative Adversarial Networks"
StyleGAN - Official TensorFlow Implementation
tqchen / xgboost
Forked from dmlc/xgboosthttps://github.com/dmlc/xgboost
CUDA implementation of the Floyd-Warshall All pairs shortest path graph algorithm(with path reconstruction)
Efficient 3D human pose estimation in video using 2D keypoint trajectories
Data Apps & Dashboards for Python. No JavaScript Required.
Repository for 3D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Image [BMVC 2018]
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.