ashish1405

@sourabh2k15 Can you please share the Indian number plates pretrained weights. Thanks

Thanks sourabh, for your inputs. But seeing the scenario for indian number plates(with hand painted/fancy fonts) will it not be advisable to use neural network like TF rather than Tesseract...

That is true, we need huge data set (more than 1 lac). Also another problem is AFAIK deep-anpr would not be able to do ocr for two line number plates...

I know this is old, but if anyone faces this issue, try to replace the code in `client.py - ONVIFService - __init__` From ```python self.create_type = lambda x: self.zeep_client.get_element('ns0:' +...

@535064094 your steps works, I've successfully installed iOSOpenDev on OSX 10.10 and XCode 7.2. There are few minor changes though in your steps. You can check the modified steps at...

@535064094 yes definitely, I also wrote you a mail regarding the same.

it should be `gte(scene\,0)` I guess.