Pinned Repositories
360SD-Net
360° Stereo Depth Estimation with Learnable Cost Volume
A-TVSNet
Code for "A-TVSNet: Aggregated Two-View Stereo Network for Multi-View Stereo Depth Estimation"
AiProducts-Challenge
In CVPR 2020 AliProducts Challenge: Large-scale Product Recognition, we got error rate 0.099 and ranked No.6. The model wil get higher score if using deeper backbone, larger bachsize or larger resolution.
BBAVectors-Oriented-Object-Detection
[WACV2021] Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors
cartreader
A shield for the Arduino Mega that can back up video game cartridges.
cnn-explainer
Learning Convolutional Neural Networks with Interactive Visualization.
DOOM
DOOM Open Source Release
DOOM-3
Doom 3 GPL source release
DRN_CVPR2020
Code and Dataset for CVPR2020 "Dynamic Refinement Network for Oriented and Densely Packed Object Detection"
dtr-prototype
Dynamic Tensor Rematerialization prototype (modified PyTorch) and simulator. Paper: https://arxiv.org/abs/2006.09616
daiszh's Repositories
daiszh/A-TVSNet
Code for "A-TVSNet: Aggregated Two-View Stereo Network for Multi-View Stereo Depth Estimation"
daiszh/DRN_CVPR2020
Code and Dataset for CVPR2020 "Dynamic Refinement Network for Oriented and Densely Packed Object Detection"
daiszh/360SD-Net
360° Stereo Depth Estimation with Learnable Cost Volume
daiszh/AiProducts-Challenge
In CVPR 2020 AliProducts Challenge: Large-scale Product Recognition, we got error rate 0.099 and ranked No.6. The model wil get higher score if using deeper backbone, larger bachsize or larger resolution.
daiszh/BBAVectors-Oriented-Object-Detection
[WACV2021] Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors
daiszh/cartreader
A shield for the Arduino Mega that can back up video game cartridges.
daiszh/cnn-explainer
Learning Convolutional Neural Networks with Interactive Visualization.
daiszh/DeepFaceLab
DeepFaceLab is the leading software for creating deepfakes.
daiszh/DOOM
DOOM Open Source Release
daiszh/dtr-prototype
Dynamic Tensor Rematerialization prototype (modified PyTorch) and simulator. Paper: https://arxiv.org/abs/2006.09616
daiszh/FerroFetchFirmware
Firmware for the Applied Procrastination "Fetch" ferrofluid display
daiszh/FinRL
FinRL: Financial Reinforcement Learning. 🔥
daiszh/genshin_auto_fish
基于深度强化学习的原神自动钓鱼AI
daiszh/GFPGAN
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
daiszh/HuEditorGenerator
The generator of Hu editor's style.
daiszh/image_harmonization
Official implementation of "Foreground-aware Semantic Representations for Image Harmonization" https://arxiv.org/abs/2006.00809
daiszh/jd_maotai_seckill
优化版本的京东茅台抢购神器
daiszh/manhattan_sdf
Code for "Neural 3D Scene Reconstruction with the Manhattan-world Assumption" CVPR 2022 Oral
daiszh/non-hair-FFHQ
A dataset that contains 6,000 non-hair FFHQ portraits.
daiszh/PhysDreamer
Code for PhysDreamer
daiszh/PointNetLK
daiszh/pytorch-meta
A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch
daiszh/PyTorchTricks
Some tricks of pytorch... :star:
daiszh/Quake-2
Quake 2 GPL Source Release
daiszh/RAFT
daiszh/review_object_detection_metrics
Object Detection Metrics. 14 object detection metrics: mean Average Precision (mAP), Average Recall (AR), Spatio-Temporal Tube Average Precision (STT-AP). This project supports different bounding box formats as in COCO, PASCAL, Imagenet, etc.
daiszh/rknn-toolkit
daiszh/SE-SSD
SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud, CVPR 2021.
daiszh/TWIST
Official codes: Self-Supervised Learning by Estimating Twin Class Distribution
daiszh/yarntown
yarntown game