Yakhyokhuja Valikhujaev

Could you add me to your wechat group? How can I join to the group. ps: I have never used wechat before so now I don't know what to do.

Thank you

Hi @kouxichao, I also having similar issue but even worse result on **143th epoch**: ``` Loading weights from checkpoint ./data/CRAFT-pytorch/real_weights/CRAFT_clr_143.pth elapsed time : 86.13623404502869spytorch/test/img_85.jpgg Calculated!{"precision": 0.0008183306055646482, "recall": 0.00048146364949446316, "hmean": 0.0006062443164595332,...

@raghavgurbaxani , @SunJJ1996 `test.py` need to be changed as follows: 1. Default score need to be set lower for `--text_threshold`. i.e, `--text_threshold=0.1` `parser.add_argument('--text_threshold', default=0.7, type=float, help='text confidence threshold')` 2. Set...

--- View raw code ```python print("Salom, Dunyo!") ``` --- Hi @callmekatootie, this is a really cool thing. I wonder why it added `;` to this code?

It's a prediction results of the model on the test set to evaluate precision, recall and hmean. When you run `eval.py` all prediction results will be written under the **submit**....

Hi @Thomnt2306 , The problem is about loading model pre-trained model. As far as I know, if you trained your model using multi-gpu setting then your weights' dictionary will be...

1. Did you train the model with multi-gpu? 2. Does your device have more than one GPU devices? 3. Did not you make any changes during model saving? If 'Yes'...

Could you print model parameters? ``` for param_tensor in net.state_dict(): print(param_tensor) ```

I think using rgb images does not help because of the network input has one channel default . However you can change it by `opt.rgb=True`.