search

gwxie / Document-Dewarping-with-Control-Points

Document Dewarping with Control Points
MIT License
156 stars 33 forks source link

About train.py #13

Open zxy-0714 opened 2 years ago

zxy-0714 commented 2 years ago

Hello, there are some problems when I run the train.py as you said.Could you give me some help?
try: FlatImg.validateOrTestModelV3(epoch, trian_t, validate_test='v_l4') FlatImg.validateOrTestModelV3(epoch, 0, validate_test='t') except: print(' Error: validate or test') the training output：【 Error: validate or test'】，I want to know what the function of this code ? Will this error affect the training process? Looking forward to your reply！

gwxie commented 2 years ago

Hello, there are some problems when I run the train.py as you said.Could you give me some help? try: FlatImg.validateOrTestModelV3(epoch, trian_t, validate_test='v_l4') FlatImg.validateOrTestModelV3(epoch, 0, validate_test='t') except: print(' Error: validate or test') the training output：【 Error: validate or test'】，I want to know what the function of this code ? Will this error affect the training process? Looking forward to your reply！

Hi, This is used to visualize the unwarped image. Does not affect training.

The file path may not be found in https://github.com/gwxie/Document-Dewarping-with-Control-Points/blob/ba4639ff1a0c8884d549e7fae3a9bddf1bef14ab/Source/utilsV4.py#L90

If the validation image was not saved during generation, You can specify ‘perturbed_img‘.