Closed LKssssZz closed 1 year ago
Thanks for your questions.
Thank you for your reply and suggestions, I will do further experiments in the future.
First of all thank you for your team's work!
My own dataset has 3k training samples and I wish to train from scratch using res50, this facilitates subsequent changes to the different backbone network. I have some questions that I hope will be answered:
- If I don't use your publicly available pretrained weights, will the network use the pretrained weights of res50 obtained on the imagenet dataset by default?
- At present, I have performed preliminary training. When using the default hyperparameters, I use 4 img/GPU 2 to train 100 epochs, and the result is still basically 0. Do I need more training cycles? How much?
thanks for your reply
同学你好,我遇到了和你一样的问题,请问是否可以加个QQ,详细的交流一下呢?谢谢您!我的QQ是755476579
同学你好,抱歉我目前仍旧有一些工作需要处理,所以抱歉抽不出时间添加同学你的qq,但是我可以给你一些我当时的思路。
以上
917481832 @.***
------------------ 原始邮件 ------------------ 发件人: "IDEA-Research/DAB-DETR" @.>; 发送时间: 2024年4月16日(星期二) 下午4:11 @.>; @.>;"State @.>; 主题: Re: [IDEA-Research/DAB-DETR] I want to train my own dataset from scratch, but have some doubts (Issue #56)
First of all thank you for your team's work!
My own dataset has 3k training samples and I wish to train from scratch using res50, this facilitates subsequent changes to the different backbone network. I have some questions that I hope will be answered:
If I don't use your publicly available pretrained weights, will the network use the pretrained weights of res50 obtained on the imagenet dataset by default?
At present, I have performed preliminary training. When using the default hyperparameters, I use 4 img/GPU 2 to train 100 epochs, and the result is still basically 0. Do I need more training cycles? How much?
thanks for your reply
同学你好,我遇到了和你一样的问题,请问是否可以加个QQ,详细的交流一下呢?谢谢您!我的QQ是755476579
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you modified the open/close state.Message ID: @.***>
First of all thank you for your team's work!
My own dataset has 3k training samples and I wish to train from scratch using res50, this facilitates subsequent changes to the different backbone network. I have some questions that I hope will be answered:
If I don't use your publicly available pretrained weights, will the network use the pretrained weights of res50 obtained on the imagenet dataset by default?
At present, I have performed preliminary training. When using the default hyperparameters, I use 4 img/GPU 2 to train 100 epochs, and the result is still basically 0. Do I need more training cycles? How much?
thanks for your reply