-
Does ic15_itn_resnet.caffemodel means train in the icdar2015 data and msra_itn_resnet.caffemodel means train in the MSRA data ? why not use icdar2015 and msra to trian a single model?
@zlmzju
-
Hi,
I'm trying to reproduce the result in the paper which are,
 using the same GTUtility and InputGenerators,…
ghost updated
5 years ago
-
1,why do detection_filtering in the [Deteval.py ](https://github.com/cs-chan/Total-Text-Dataset/blob/9ed8b6ad0475e235b26849bfb47a7943265132c7/Evaluation_Protocol/Python_scripts/Deteval.py#L86)
2,why …
xiliu updated
5 years ago
-
I run the east_icdar2015_resnet_v1_50_rbox model/model.ckpt-49491 on ICDAR2015-TRW public_test_data, then test the result with the detection_eval_tool but only get 0.4697 F1-score. I don't know what w…
-
最近我用师兄您在github上复现的R2CNN的代码，感觉师兄你写得很棒，在此表示尊敬和佩服，向师兄你学习！
我的想法是用ICDAR2015数据集来训练，然后再用于天池之前那个比赛的数据集来训练，虽然比赛期间没有做出来，后来一直不甘心，想把这个愿望实现。
我根据您github上的步骤来训练，我对ICDAR数据集也做了处理，把它做成了VOC的格式，但我不知做的是否正确，我将做好的Annotati…
-
师兄您好！ 可以提供一下icdar2015转voc格式的代码吗，我自己处理后训练出来的结果和你的好差很大 感觉很神奇 处理完的icdar2015的数据我可视化出来和原本的gt_txt可视化是接近的 证明是没有错误的 还有我的坐标调整到了顺时针
-
Hello and thank you for your efforts to make things simple.
I have trained icdar2015 data through your repo
You left everything default
I already got a good test accuracy
The implementation time i…
ghost updated
5 years ago
-
Thank you for your code! I trained the icdar2015 for using your code, I iterated 10w times, but i can't not get the result same as you. I modified the the anchor_scale to be [1/2, 1.] in the cfgs.py. …
-
1. After rotating the bounding box, we can't change the size of bounding box with keeping the shape of it as a rectangular. Could you add some constraints?
2. A possible improvement is to provide mor…