messileo1 Goto Github PK

clash-for-linux-backup

clash for linux备份仓库

clash-for-windows_chinese

clash for windows汉化版. 提供clash for windows的汉化版, 汉化补丁及汉化版安装程序

dropblock

Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.

edge-dectection_canny-otsu

Implementation for the paper "Han et al., 2013, Research and Implementation of an Improved Canny Edge Detection Algorithm"

efficient_yolov4

efficientnet-yolo3-pytorch

这是一个efficientnet-yolo3-pytorch的源码，将yolov3的主干特征提取网络修改成了efficientnet

efficientnetb0_yolov4

将主干替换为efficientnetb0，主干权重文件自行下载

external-attention-pytorch

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

focal_loss_pytorch

A PyTorch Implementation of Focal Loss.

get_ap_recall_precision_f1

将每个预测类别的score以score对应的RECALL、PRECISION、F1在控制台打印出来，而AP曲线的数据在result文件夹下面的TXT文件里有

how_to_train_yolo

如何训练与测试YOLO，以及其中的一些注意事项，版本不断更新中

image-augmentation

knowledge_distillation

知识蒸馏代码，可视化

leetcode-master

《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！🚀

load_weights_test

加载权重的两种方式及网络测试，权重文件和yolov4_tiny这个Respository是一样的

lsd_for_detect

mmdeploy

OpenMMLab Model Deployment Framework

mmdetection

OpenMMLab Detection Toolbox and Benchmark

mmrazor

OpenMMLab Model Compression Toolbox and Benchmark.

mobilenet-yolov4-pytorch

这是一个mobilenet-yolov4的库，把yolov4主干网络修改成了mobilenet，修改了Panet的卷积组成，使参数量大幅度缩小。

mobilenet_ghostnet_densenet_resnet_vgg_yolov4

主干特征提取网络为MobileNet_GhostNet_DenseNet_ResNet_Vgg的Yolov4

new_lossfunction

nothing

object-detection-augmentation

这里面存放了一些目标检测算法的数据增强方法。如mosaic、mixup。

object-detection-usages

The brief implementation and using examples of object detection usages like, IoU, NMS, soft-NMS, SmoothL1、IoU loss、GIoU loss、 DIoU loss、CIoU loss, cross-entropy、focal-loss、GHM, AP/MAP and so on by Pytorch.

power-line-detection

Code for detecting power lines in images using OpenCV

pytorch-loss

label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful

repdistiller

[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

ros_21_tutorials

《古月 · ROS入门21讲》课件&源码

serial0816

serial_comm

2023.08.15晚上测试通过虚拟串口通过ROS节点订阅话题消息并打印出来