search

princewang1994 / TextSnake.pytorch

A PyTorch implementation of ECCV2018 Paper: TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes
https://arxiv.org/abs/1807.01544
MIT License
437 stars 92 forks source link

can icdar2015 dataset be used in this modle? #6

Closed Jackandrome closed 5 years ago

Jackandrome commented 5 years ago

does the total_text.py can only deal with curved texts ?

princewang1994 commented 5 years ago

Yes, code in total_text.py assumes that gt are given with polygon(x0, y0, x1, y1..., xn, yn) format, so icdar(rectangle text annotation) can be used if you treat annotations as a quadrangles(x0, y0, x1, y1, x2, y2, x3, y3).

Jackandrome commented 5 years ago

thank you for your response I don't really use pytorch,so when I'm running your code, I got this error: DataLoader worker (pid 1008) exited unexpectedly with exit code 1.

so I can't load data,eventhough I changed the batch size into 1 , could you help me with that?

princewang1994 commented 5 years ago

@Jackandrome can you provide the exact error output and the full exception track stack?

Jackandrome commented 5 years ago

@princewang1994

-`Traceback (most recent call last): File "train.py", line 158, in main() File "train.py", line 144, in main train(model, train_loader, criterion, scheduler, optimizer, epoch) File "train.py", line 51, in train output = model(img) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 477, in call result = self.forward(*input, kwargs) File "/home/fuzilong/TextSnake/network/textnet.py", line 40, in forward C1, C2, C3, C4, C5 = self.backbone(x) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 477, in call result = self.forward(*input, *kwargs) File "/home/fuzilong/TextSnake/network/vgg.py", line 17, in forward C1 = self.stage1(x) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 477, in call result = self.forward(input, kwargs) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/container.py", line 91, in forward input = module(input) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 477, in call result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/conv.py", line 301, in forward self.padding, self.dilation, self.groups) File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 227, in handler _error_if_any_worker_fails()

RuntimeError: DataLoader worker (pid 4322) is killed by signal: Bus error. Details are lost due to multiprocessing. Rerunning with num_workers=0 may give better error trace. `

If i let the num_worker= 0 , there is no error ,but the data loading is very slow.

princewang1994 commented 5 years ago

Sorry I cannot reproduce this error, but someone else met the same error on this issue. May using the same python environment or pytorch version will help you.