search

jkjung-avt / yolov4_crowdhuman

A tutorial on training a DarkNet YOLOv4 model for the CrowdHuman dataset
MIT License
140 stars 49 forks source link

cannot download yolov4-crowdhuman-416x416_best.weights #28

Open fatfishlin opened 2 years ago

fatfishlin commented 2 years ago

hi,I am from China,I wan to download your yolov4-crowdhuman-416x416_best.weights,but ,in China ,everyone can not open google website ,so I can not download yolov4-crowdhuman-416x416_best.weights, would you please send me one copy file,or other ways? thanks

jkjung-avt commented 2 years ago

If you provide an online storage space, I could upload the files for you.

fatfishlin commented 2 years ago

thanks，I have no online storage space,would you please send me using wechat(ID: 13487268841),or ,send me to this email? are you from TaiWan? your jetson projects are very good,I will add star for you.

thanks again.

At 2021-12-19 11:58:23, "JK Jung" @.***> wrote:

If you provide an online storage space, I could upload the files for you.

— Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you authored the thread.Message ID: @.***>

jkjung-avt commented 2 years ago

Yes, I'm located in Taiwan.

The files are too large to be sent via email. And I don't use WeChat to send files. Please propose other alternatives.

fatfishlin commented 2 years ago

please upload weights files in:

https://drive.google.com/drive/folders/1OnUSmXMGkCl3w1BvvEwWzibgPnAoPadg?usp=sharin

thanks very much!

jkjung-avt commented 2 years ago

Done uploading...

fatfishlin commented 2 years ago

thanks., people detection can be done using yolov4-crowdhuman-416x416_best.weights,yolov4-crowdhuman-608x608.weights and your yolov4-608.weights(demo #5 in your url:https://github.com/jkjung-avt/tensorrt_demo). which one can get best accuracy? which one are the best choice on jetson AGX? thanks

jkjung-avt commented 2 years ago

which one can get best accuracy?

"yolov4-crowdhuman-608x608" could detect smaller people in the picture.

which one are the best choice on jetson AGX?

This depends on the requirements of your application. For example,

circularProteus commented 2 years ago

please upload weights files in:

https://drive.google.com/drive/folders/1OnUSmXMGkCl3w1BvvEwWzibgPnAoPadg?usp=sharin

thanks very much!

could you pls also upload tiny version?

jkjung-avt commented 2 years ago

@circularProteus Sorry, I don't keep yolov4-tiny-crowdhuman weights around. It shouldn't take long to train one, though.