zyg11's repositories
bytetrack-opencv-onnxruntime
分别使用OpenCV、ONNXRuntime部署ByteTrack目标跟踪,包含C++和Python两个版本的程序
Conformer
Official code for Conformer: Local Features Coupling Global Representations for Visual Recognition
CrossPoint
Official implementation of "CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding" (CVPR, 2022)
deep_sort_pytorch
MOT using deepsort and yolov3 with pytorch
deformable-detr-annotations
deformable-detr-annotations
face-alignment
:fire: 2D and 3D Face alignment library build using pytorch
lc
《代码随想录》LeetCode 刷题攻略:200道经典题目刷题顺序,共60w字的详细图解,视频难点剖析,50余张思维导图,支持C++,Java,Python,Go,JavaScript等多语言版本,从此算法学习不再迷茫!🔥🔥 来看看,你会发现相见恨晚!🚀
libface-sface_detect-recognition-opencv
使用OpenCV部署libface人脸检测和SFace人脸识别,包含C++和Python两种版本的程序,仅仅只依赖OpenCV库就能运行
MAE-pytorch
Masked Autoencoders Are Scalable Vision Learners
MapTR
[ICLR'23 Spotlight] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
mmfewshot
OpenMMLab FewShot Learning Toolbox and Benchmark
MOS-Multi-Task-Face-Detect
Code for BMVC2021 "MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation"
od_konwledge_distill
An Object Detection Knowledge Distillation framework powered by pytorch, now having SSD and yolov5.
OpenOccupancy
OpenOccupancy
PINTO_model_zoo
A repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]
pytorch-ssd-for-ZQCNN
用pytorch训练ssd,相比原版pytorch-ssd改动了不少
RangeDet
Paper and Codes for “RangeDet: In Defense of Range View for LiDAR-based 3D Object Detection” (ICCV2021)
RMNet
RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.
simple_occupancy
An intuitive approach for 3D Occupancy Detection
SPr
[ICCV 2023] StreamPETR: Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection
yolov5-rt-stack
yolort / yet another yolov5, with its runtime stack for libtorch, onnx, tvm, ncnn and specialized accelerators.