一、地址来源
YOLOv4最全复现代码合集（含PyTorch/TF/Keras和Caffe等）
二、Pytorch版本
地址：https://github.com/Tianxiaomo/pytorch-YOLOv4 这个地址支持训练
Requirements and Dependencies
pip install numpy==1.18.2
CPU only
pip install torch==1.4.0+cpu torchvision==0.5.0+cpu -f https://download.pytorch.org/whl/torch_stable.html
pip install tensorboardX==2.0
pip install scikit_image==0.16.2
pip install matplotlib==2.2.3
pip install tqdm==4.43.0
pip install easydict==1.9
pip install Pillow==7.1.2
pip install skimage
pip install opencv_python==4.1.2.30
pip install pycocotools
三、Tensorflow版本
Requirements and Dependencies
https://download.pytorch.org/whl/torch_stable.html
pip install scikit_image==0.16.2
pip install tensorflow==2.3.0
pip install easydict==1.9
pip install Pillow==7.1.2
pip install opencv_python==4.1.2.30
Original: https://blog.csdn.net/seek97/article/details/122326857
Author: 南叔先生
Title: YOLOv3(Pytorch版本和Tensorflow版本）学习
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/497576/
转载文章受原作者版权保护。转载请注明原作者出处！