5

I start the course of tensorflow in udacity, and simultaneously I am looking on the web for the topic.

I suppose that the typical use cases are well solved already, in a better way that i can achieve by my own. In other words in some place exists trained models for usual cases ready to use. I found zooModels that if I undestand properly is the thing that i looking for. but I can't realize that there does not exist a ocr model published that can recognise a number in a image:

image example

Do i need to train my own model? Is there a repository that i don't know?

gdelab
  • 6,124
  • 2
  • 26
  • 59
mls_dev
  • 511
  • 2
  • 6
  • 21
  • I don't think it exists unfortunately. But you can probably adapt the street view models, for which there is already a lot already done [here](https://github.com/tensorflow/models/tree/master/research/street) – gdelab Dec 22 '17 at 15:26

0 Answers0