-
i want to only test the acc of Structure recognition accuracy and use mmocr_teds_acc_mp.py, then i use pretrain model name as you supply epoch_16_0.7767.pth, to get only table structure results
…
-
Hi @huningxin and the team, thank you for your extensive work!
## TLDR
1. Is installing [opencv.js from NPM](https://www.npmjs.com/package/opencv.js) the recommended way to use in Node/browsers?…
-
How to convert **psenet_r50_fpnf_600e_icdar2015_pretrain-eefd8fe6.pth** model to torch jit model , when i tried so i am getting an error of
The code which i used to convert is
`def convert_model(m…
-
-
### **question**
I deployed a model using torchserve, batchsize=8, workers=1. When eight small images(wxh:721x222) are tested at the same time, torchserve can respond quickly and process them in the …
-
**Describe the bug**
If I print ```results``` variable [here](https://github.com/open-mmlab/mmocr/blob/d7fa9544e623bc1c1205ac3172b522b0b45918e3/mmocr/datasets/pipelines/ocr_transforms.py#L86), I obta…
-
![2222222](https://user-images.githubusercontent.com/20136991/86200346-f649c000-bb8e-11ea-8b92-dfa08ecc90ff.png)
>>> tensorflow.__version__
'1.13.1'
>>> torch.__version__
'1.5.0+cpu'
>>> torc…
-
rt。。。发现最后的结果边界都比较差,会往内缩一点,不知道是不是我迭代的次数太少了,但是600个epoch也太长了吧,现在我一般只训50个epoch左右,600个估计一个星期能有一个结果
-
Hi @wenwenyu , Please provide some information on the OCR module also... that will be really helpful. How are you extracting text from the test images? Are you using Tessaract or some other API? Is t…
-