Recall and precision on ICDAR2013

Question

Recall and precision on ICDAR2013

lyc6749 opened this issue 5 years ago · 12 comments

lyc6749 commented 5 years ago

How about the recall and precision on ICDAR2013 by your implemention？

mayank-git-hub commented 5 years ago

Yep

Answer 1 · 2019-08-26T12:49:51.000Z

Can you provide this file？

Answer 2 · 2019-08-27T04:30:15.000Z

Hey, Sorry for the delayed reply. I have been sick for a few days. Will solve the bugs in the master by the end of the day. Thank You for your patience.

Answer 3 · 2019-08-27T17:32:34.000Z

How about the recall and precision on ICDAR2013 by your implemention？

The weak supervision code seems to be working. I have updated the master branch to incorporate the changes. I will train the model tomorrow on IC13, IC15 and send the link to the pre-trained model, Generated character Bounding Boxes, and F-score.

Thank You for your patience.

Answer 4 · 2019-09-01T14:51:46.000Z

Hi @mayank-git-hub , thanks for your code. Do you mind telling me that what is the performance of the pre-trained model on ICDAR 13 dataset?

Answer 5 · 2019-09-01T15:42:17.000Z

Currently the performance is not good. I am able to achieve an approximate F-score of 70. I am tweaking and experimenting to improve the results. Will update the ReadMe file with the F-scores of all the datasets.

Answer 6 · 2019-09-01T16:17:35.000Z

Thanks for your reply. I am also working on the training code. And also only could get 0.71 H-mean on IC13 dataset. Looking for your results.

Answer 7 · 2019-09-01T16:25:17.000Z

Great, I am also working on it. Would update the Readme file as soon as I get better results. Thank You for your patience.

Answer 8 · 2019-09-09T06:59:23.000Z

@mayank-git-hub Quick question, 0.7051 F1 Score on IC13 is with CRAFT or ResNet CRAFT ? Which one is better and by how much ?

Thanks ;)

Answer 9 · 2019-09-09T07:03:28.000Z

The f score is with craft model with vgg backbone. Haven't tried resnet unet architecture.

Answer 10 · 2019-09-09T08:01:57.000Z

Thanks @mayank-git-hub. Btw, I saw you included link to Original Model by authors in the README. Can we load that model and fine tune it with this code ?

Answer 11 · 2019-09-09T08:07:06.000Z

Thanks @mayank-git-hub. Btw, I saw you included link to Original Model by authors in the README. Can we load that model and fine tune it with this code ?

Yep we can ;)