awesome-semantic-segmentation-pytorch icon indicating copy to clipboard operation
awesome-semantic-segmentation-pytorch copied to clipboard

Published 20 hours ago • verified publisher icon Tramac

Trainning my own dataset

Open casiahnu opened this issue 5 years ago • 11 comments

Each image in my dataset is 256*256, and is divided into two categories: background and subject. It contains -train --image --mask -test --image --mask

Could you please tell me which dataloader.py should I refer and modify? Thank You!

casiahnu avatar Apr 17 '20 08:04 casiahnu

I have the same problem.

zuo-ux avatar Apr 19 '20 11:04 zuo-ux

hi, did you solve it? I have the same problem. @casiahnu @zuo-ux

lichen14 avatar Apr 23 '20 03:04 lichen14

hi, did you solve it? I have the same problem. @casiahnu @zuo-ux

no

zuo-ux avatar Apr 23 '20 09:04 zuo-ux

It is best to modify on cityscapes.py. Do you have WeChat？I have not had enough time to follow github recently, maybe solve the problem by WeChat.

Tramac avatar Apr 23 '20 09:04 Tramac

It is best to modify on cityscapes.py.

how to operate dataloader？

zuo-ux avatar Apr 23 '20 09:04 zuo-ux

It is best to modify on cityscapes.py. Do you have WeChat？I have not had enough time to follow github recently, maybe solve the problem by WeChat.

Thank you. My wechat is 18810220665. What's the function of segbase.py? Look forward to your reply.

casiahnu avatar Apr 23 '20 10:04 casiahnu

It is best to modify on cityscapes.py. Do you have WeChat？I have not had enough time to follow github recently, maybe solve the problem by WeChat.

Thank you!My wechat is 18761601876,Look forward to your reply.

zuo-ux avatar Apr 24 '20 02:04 zuo-ux

@casiahnu Hi,did you solve the problem?

QianSiWang1 avatar May 03 '20 11:05 QianSiWang1

@zuo-ux Hi,did you solve the problem?

QianSiWang1 avatar May 15 '20 15:05 QianSiWang1

It is best to modify on cityscapes.py. Do you have WeChat？I have not had enough time to follow github recently, maybe solve the problem by WeChat.

Thank you!My wechat is 18761601876,Look forward to your reply.

Have you added wechat and solved your problem??

Zhang-O avatar May 25 '20 00:05 Zhang-O

Each image in my dataset is 256*256, and is divided into two categories: background and subject. It contains -train --image --mask -test --image --mask

Could you please tell me which dataloader.py should I refer and modify? Thank You!

Hi, I met the same problem. I've already written a dataloader file and renamed it to mydata.py for example. I also added the name "mydata" in code as an argument. But when I ran the command " python train.py --model fcn32s --backbone vgg16 --dataset mydata --lr 0.01 --epochs 50" ,the error occured: train.py: error: argument --dataset: invalid choice: 'mydata' (choose from 'pascal_voc', 'pascal_aug', 'ade20k', 'citys', 'sbu') Do u know what should I modify then? Thanks for ur help!

Kittywyk avatar Sep 14 '20 11:09 Kittywyk