CRAFT-Reimplementation

CRAFT-Reimplementation copied to clipboard

您好，这个项目的还会完善吗？

pengfan-ui

微信二维码不能用了，能重新发一下吗

85

zhouguanghui001

RuntimeError: each element in list of batch should be of equal size

8

I get this error when I run `python trainSynth.py` with [SynthText](https://academictorrents.com/details/2dba9518166cbd141534cbf381aa3e99a087e83c) as dataset Traceback (most recent call last): File "/usr/local/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 521, in __next__ data = self._next_data() File "/usr/local/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line...

ghost

fine-tuning on a custom dataset with the official craft-pytorch weights

4

Hello, is it possible to fine-tune your model on a custom dataset with Craft-PyTorch released weights too?

alikaz3mi

The test accuracy is lower than README.md mentioned

5

Thanks for reimplementation. I use the release weights to run the model, but the test results are lower than README.md mentioned. text_threshold=0.7 low_text=0.4 link_threshold=0.4 Syndata+IC13+IC17 test on icdar2013: "precision": 0.8733264675592173,...

Laeglaur

Hi before anything thanks to this repo but I can't find weights for inference could you please help me?

AtefehBaniasadi

where is weights_7000.pth, can u provide link to download it please

dotrungkien3210

Weakly supervised problem

4

Hi author, thanks for opening source your reimplementation about CRAFT. I hope to get the same results as claimed in the original paper, but now still have some problems (only...

lianqing01

Dimensions of character boxes out of bounds on multiple epochs

1

**Found a small bug:** On traversing through same image in multiple epochs and hence doing random_scaling every time, the coordinates in the previous epch get mutliplied by the scale factor...

vasusharma7

Hello in part 3.2.2 of the main paper related to this CRAFT-Reimplementation, the authors say : " When a real image with word-level annotations is provided, the learned interim model...

Alikavari