search

ruizengalways / PFNet

Code Repo of 'Rethinking Planar Homography Estimation Using Perspective Fields'
35 stars 10 forks source link

Train custom dataset #1

Open blueclowd opened 4 years ago

blueclowd commented 4 years ago

Hi @ruizengalways

Thanks for sharing the code. May I know if there is any tutorial showing how to train a custom dataset apart from COCO? Thanks

ruizengalways commented 4 years ago

You can use next() to iterate the dataset generator to know the details inside. I think it is not too hard to extend the generator to other datasets

SuperDetected commented 4 years ago

Excuse me! Thanks for your codes.When I use your codes to train in the dataset COCO, the loss is always at 11.xx, and the MACE is always at 24.xx.They never go down.Could you tell me if there are something to adjust?

ruizengalways commented 4 years ago

Excuse me! Thanks for your codes.When I use your codes to train in the dataset COCO, the loss is always at 11.xx, and the MACE is always at 24.xx.They never go down.Could you tell me if there are something to adjust?

How many epochs have you already trained? Could you please give me more details about your training?

SuperDetected commented 4 years ago

Thanks for your reply,I trained the dataset just with the epochs you have set in the codes:

And the only thing I changed is the IMAGES_PER_GPU,the original value is 32 and I set it 2 like this:

------------------ 原始邮件 ------------------ 发件人: "Rui Zeng"<notifications@github.com>; 发送时间: 2020年5月27日(星期三) 上午10:03 收件人: "ruizengalways/PFNet"<PFNet@noreply.github.com>; 抄送: "知足~奔跑"<2563163858@qq.com>;"Comment"<comment@noreply.github.com>; 主题: Re: [ruizengalways/PFNet] Train custom dataset (#1)

Excuse me! Thanks for your codes.When I use your codes to train in the dataset COCO, the loss is always at 11.xx, and the MACE is always at 24.xx.They never go down.Could you tell me if there are something to adjust?

How many epochs have you already trained? Could you please give me more details about your training?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

ruizengalways commented 4 years ago

Increase the batch size and decrease the learning rate

Thanks for your reply,I trained the dataset just with the epochs you have set in the codes: And the only thing I changed is the IMAGES_PER_GPU,the original value is 32 and I set it 2 like this: … ------------------ 原始邮件 ------------------ 发件人: "Rui Zeng"<notifications@github.com>; 发送时间: 2020年5月27日(星期三) 上午10:03 收件人: "ruizengalways/PFNet"<PFNet@noreply.github.com>; 抄送: "知足~奔跑"<2563163858@qq.com>;"Comment"<comment@noreply.github.com>; 主题: Re: [ruizengalways/PFNet] Train custom dataset (#1) Excuse me! Thanks for your codes.When I use your codes to train in the dataset COCO, the loss is always at 11.xx, and the MACE is always at 24.xx.They never go down.Could you tell me if there are something to adjust? How many epochs have you already trained? Could you please give me more details about your training? — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

SuperDetected commented 4 years ago

OK, I will have a try,thanks.

------------------ 原始邮件 ------------------ 发件人: "Rui Zeng"<notifications@github.com>; 发送时间: 2020年5月27日(星期三) 下午3:07 收件人: "ruizengalways/PFNet"<PFNet@noreply.github.com>; 抄送: "知足~奔跑"<2563163858@qq.com>;"Comment"<comment@noreply.github.com>; 主题: Re: [ruizengalways/PFNet] Train custom dataset (#1)

Increase the batch size and decrease the learning rate

Thanks for your reply,I trained the dataset just with the epochs you have set in the codes: And the only thing I changed is the IMAGES_PER_GPU,the original value is 32 and I set it 2 like this: … ------------------ 原始邮件 ------------------ 发件人: "Rui Zeng"<notifications@github.com>; 发送时间: 2020年5月27日(星期三) 上午10:03 收件人: "ruizengalways/PFNet"<PFNet@noreply.github.com>; 抄送: "知足~奔跑"<2563163858@qq.com>;"Comment"<comment@noreply.github.com>; 主题: Re: [ruizengalways/PFNet] Train custom dataset (#1) Excuse me! Thanks for your codes.When I use your codes to train in the dataset COCO, the loss is always at 11.xx, and the MACE is always at 24.xx.They never go down.Could you tell me if there are something to adjust? How many epochs have you already trained? Could you please give me more details about your training? — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.