工程（五）——小目标检测tph-yolov5

 1、环境安装

1、创建环境
conda create -n yolo python=3.7
conda activate yolo
2、安装pytorch
conda install pytorch torchvision cudatoolkit=11.3 -c pytorch
3、克隆代码
git clone https://github.com/cv516Buaa/tph-yolov5
cd tph-yolov5
pip install -i https://pypi.tuna.tsinghua.edu.cn/simple -r requirements.txt  
4、yolov5 报错AttributeError: ‘Upsample‘ object has no attribute ‘recompute_scale_factor
根据自己电脑cuda执行相应命令
# CUDA 10.2
conda install pytorch==1.9.0 torchvision==0.10.0 torchaudio==0.9.0 cudatoolkit=10.2 -c pytorch
# CUDA 11.3
conda install pytorch==1.9.0 torchvision==0.10.0 torchaudio==0.9.0 cudatoolkit=11.3 -c pytorch -c conda-forge
# CPU Only
conda install pytorch==1.9.0 torchvision==0.10.0 torchaudio==0.9.0 cpuonly -c pytorch

2、数据下载

Datasets: [VisDrone](http://aiskyeye.com/download/object-detection-2/)
Weights(PyTorchv1.10):
 yolov5l-xs-1.pt: (https://pan.baidu.com/s/1APETgMoeCOvZi1GsBZERrg)
 yolov5l-xs-2.pt: (https://pan.baidu.com/s/19S84EevP86yJIvnv9KYXDA)

3、测试

python detect.py --source ./data/images/ --weights weights/yolov5l-xs-1.pt --conf 0.4