For the dateset of images that will be provided, you have to create your own deep learning based OCR model
The OCR model should have following properties:
A. Should have an accuracy of more than 95% in the dataset that I will provide
B. Should have an inference time of less than 200ms
C. Should have very low computational load
D. Preferred programming language for the application: Python. If build in any other application, you have to provide and API access to request and get response from the application
E. After completion of the application, you have to give a short Knowledge Transfer session of how the code is built and how did the model training happen, how to train it on our own for further works on top of the application
F. What frameworks do you use to build the application?
I am looking for individual freelancer and can provide such continuous projects
About the recuiterMember since May 20, 2018 Amol Rane
from Mecklenburg-Vorpommern, Germany