-
Thanks for your work!
In the paper, the Total-Text has GT of 10 annotated points and CTW1500 has GT of 14 annotated points. But in my custom datasets, each curve text 's number of annotated points ar…
-
Hi, thanks for your great work!
But when I train my own models on the custom dataset with only four vertices, following the [example scripts](https://universityofadelaide.box.com/s/fo7odnmqe370btm7sd…
-
Hi, thanks for your great work!
But when I run the ABCNet demo, it occurred an error.
Just for a simple test, I use the my own dataset, following your demo command:
```
python demo/demo.py \
…
-
Training with custom datasets, programing pause more than 10m with fellowing log, haven't print training meg. I have prepare dataset via example script and checked carefully with outputed dataset. An…
-
Thanks for your great work and sharing the code.
I wonder what is the number of point to annotate the curved text area.
-
Issue was generated while running test.py script with --cuda=False. Key names mismatched while loading pretrained weight with pytorch-cpu version. Resolved temporarily by adding net=torch.nn.DataParal…
-
Hi~, I've downloaded the CTW1500 model and run the demo/demo.py as you said in the tutorial. But I got this error, I'm very confused about it. I haven't modified anything yet. Can you give me some adv…
-
[05/16 21:21:18 detectron2]: Arguments: Namespace(confidence_threshold=0.5, config_file='configs/BAText/CTW1500/attn_R_50.yaml', input=['input.jpg'], opts=['MODEL.WEIGHTS', 'ctw1500_attn_R_50.pth'], o…
-
Hi, from what I understand, to generate a Bezier curve for one side of the text region, we need at least 4 points. Therefore we would need 8 points in total for a text instance. In the paper, the auth…
-
Thanks for your great work and sharing the code.
The text detection results are not available on your arxiv paper, so can you provide the text detection results(Recall/Precision/F-measure) on your da…