Training this model from scratch takes a couple minutes of a V100 GPU. Super fast.
Show this thread
Interested in learning how to build OCR models? Here's a great code example from @A_K_Nain showing a model that can break Captchas. https://keras.io/examples/vision/captcha_ocr/ …pic.twitter.com/Rh3Py2CBqp
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Now click on the squares that contain a road sign.
#sentientbeingverifiedThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Y do this, it was already difficult enough. Now it will be more challenging for a human to proove he/ she is human.
-
I gave up to do only computer enabled processes
End of conversation
New conversation -
-
-
@fchollet...
...cool would be also an example for object detection using mask-rcnn's. This is also a very interesting technique in the computer vision section.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Super!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Great!!!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Isn't StringLookup currently only available in tf-nightly?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
How does this model behave for repeated characters, like "aa", "bb" etc.? I can't see in the code any separator to differentiate between neighboring chars of the same class? This may lead to errors like the one in your example: "448de" decoded instead of "488de".
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.