luzelin's repositories
anomaly_transformer_pytorch
PyTorch implementation of Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy
BCNet
Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]
Cream
This is a collection of our NAS and Vision Transformer work.
deep-learning-for-image-processing
deep learning for image processing including classification and object-detection etc.
Detectron
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.
DSTAGNN
DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting, which is accepted at ICML2022.
Efficient-AI-Backbones
Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
ffmpeg-python
Python bindings for FFmpeg - with complex filtering support
GALD-DGCNet
Source code and models GALD net (BMVC-2019)and Dual-Seg Net (BMVC-2019)
gcn
Implementation of Graph Convolutional Networks in TensorFlow
GloRe
Global Reasoning module for visual recognition
grad-cam
[ICCV 2017] Torch code for Grad-CAM
Graph-Learning
Graph model implementation
learn-to-cluster
Learning to Cluster Faces (CVPR 2019, CVPR 2020)
LiteFlowNet
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)
Mask_RCNN
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
maskrcnn-benchmark
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
MaskRelation
Code of masked relation learning for deepfake detection
OCCNN
Implimenting one class classification with pre-trained cnn (vgg16)
OCGNN
my implement of my paper
paper-reading
深度学习经典、新论文逐段精读
PWC-Net
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.