配置yolov5s等深度学习环境

1.参考以下链接，安装anaconda：
https://www.bilibili.com/video/BV1z24y1b7Qm/?p=2&spm_id_from=pageDriver
2.参考以下链接，安装vscode+编译器选择+anaconda环境变量更改
https://www.bilibili.com/video/BV1bQ4y1n7sn?p=4&vd_source=57e45c6d673d6cbd7f32de3f945fc220

3.参考以下链接教程，安装好cuda11.3.0，cudnn8.2.1

Win10配置Yolov5虚拟环境之(安装CUDA和cuDNN和pytorch)_虚拟环境下载的cuda在哪-优快云博客

4.在anaconda prompt终端，运行以下命令安装与cuda与cudnn版本相匹配的pytorch

conda install pytorch==1.11.0 torchvision==0.12.0 torchaudio==0.11.0 cudatoolkit=11.3 -c pytorch

5.由于yolov5s中requirements.txt配置起来总是自动安装最新版本，因此，这里提供一个适合yolov5s-6.1版本的requirements.txt文件，省得运行起来各种报错，具体如下：

# pip install -r requirements.txt

# Base ----------------------------------------

matplotlib==3.5.2

numpy==1.19.5

opencv-python==4.9.0.80

Pillow==9.5.0

PyYAML==6.0.1

requests==2.25.1

scipy==1.10.1

torch==1.11.0

torchvision==0.12.0

tqdm==4.61.2

timm==0.9.16

einops==0.7.0

# Logging -------------------------------------

tensorboard==2.9.1

# wandb

# Plotting ------------------------------------

pandas==1.2.5

seaborn==0.11.0

# Export --------------------------------------

# coremltools==4.1  # CoreML export

# onnx==1.9.0  # ONNX export

# onnx-simplifier==0.3.6  # ONNX simplifier

# scikit-learn==0.19.2  # CoreML quantization

# tensorflow==2.4.1  # TFLite export

# tensorflowjs==3.9.0  # TF.js export

# openvino-dev  # OpenVINO export

# Extras --------------------------------------

# albumentations==1.0.3

# Cython  # for pycocotools https://github.com/cocodataset/cocoapi/issues/172

# pycocotools==2.0  # COCO mAP

# roboflow

thop==0.1.1.post2209072238  # FLOPs computation