xu-peng-tao / SSD-Pruning-and-quantization
Pruning and quantization for SSD. Model compression.
☆28Updated 3 years ago
Related projects: ⓘ
- ☆14Updated this week
- Based of paper "Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference"☆61Updated 3 years ago
- Using model pruning method to obtain compact models Pruned-YOLOv5 based on YOLOv5.☆57Updated 3 years ago
- In this repository using the sparse training, group channel pruning and knowledge distilling for YOLOV4,☆29Updated last year
- MobileNetV3 SSD的简洁版本☆77Updated 4 months ago
- ☆14Updated 3 years ago
- This repository provides a sample to run yolov3 on int8 mode in tensorRT☆27Updated 5 years ago
- MobileNetV3 based SSD-lite implementation in Pytorch☆97Updated 5 years ago
- An Object Detection Knowledge Distillation framework powered by pytorch, now having SSD and yolov5.☆214Updated 2 years ago
- ☆90Updated 2 years ago
- ☆32Updated 3 years ago
- Try out different pruning-approaches on lightweight Backbones.☆142Updated 4 years ago
- A resnet18 version of CenterNet（objects as points）☆124Updated 3 years ago
- This is a knowledge distillation toolbox based on mmdetection.☆73Updated 2 years ago
- QuarkDet lightweight object detection in PyTorch .Real-Time Object Detection on Mobile Devices.☆89Updated 3 years ago
- This is 8-bit quantization sample for yolov5. Both PTQ, QAT and Partial Quantization have been implemented, and present the results based…☆95Updated 2 years ago
- yolov5 onnx caffe☆111Updated 3 years ago
- www.giantpandacv.com☆149Updated 3 months ago
- Darknet(AB版)框架源码解析：详尽的中文注释(逐句)和原理分析！☆72Updated 3 years ago
- model compression based on pytorch (1、quantization: 8/4/2bits(dorefa)、ternary/binary value(twn/bnn/xnor-net)；2、 pruning: normal、regular a…☆170Updated 4 years ago
- yolov5 pruning (SFP Pruning、Nework Slimming)☆18Updated 2 years ago
- ☆13Updated 3 years ago
- pytorch AutoSlim tools，支持三行代码对pytorch模型进行剪枝压缩☆38Updated 3 years ago
- ppyolo in pytorch. 44.8% box mAP.☆105Updated 2 years ago
- RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is la…☆209Updated last year
- yolov5 5.0 version distillation || yolov5 5.0版本知识蒸馏，yolov5l >> yolov5s☆153Updated 3 years ago
- Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression (AAAI 2020)☆43Updated 2 years ago
- yolov5 onnx caffe☆84Updated 3 years ago
- A nnie quantization aware training tool on pytorch.☆238Updated 3 years ago
- 用于 MobileNetV3 在自定义数据集上的量化，模型压缩90%而精度几乎不受影响，论文：HAQ: Hardware-Aware Automated Quantization with Mixed Precision☆15Updated 3 years ago