search

Tramac / awesome-semantic-segmentation-pytorch

Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)
Apache License 2.0
2.8k stars 581 forks source link

Trainning my own dataset #126

Open casiahnu opened 4 years ago

casiahnu commented 4 years ago

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!

zuo-ux commented 4 years ago

I have the same problem.

lichen14 commented 4 years ago

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

zuo-ux commented 4 years ago

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

no

Tramac commented 4 years ago

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.

zuo-ux commented 4 years ago

It is best to modify on cityscapes.py.

how to operate dataloader？

casiahnu commented 4 years ago

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.

zuo-ux commented 4 years ago

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.

QianSiWang1 commented 4 years ago

@casiahnu Hi,did you solve the problem?

QianSiWang1 commented 4 years ago

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

Zhang-O commented 4 years ago

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??

Kittywyk commented 3 years ago

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!