I found the code to be extremely clear and concise -- huge respect for the author (who was kind enough to put up with our lengthy code reviews) 
Show this thread
New code example on http://keras.io : implement and train a RetinaNet object detection pipeline from scratch in Keras - in a bit over 400 lines of code. Created by @srihari_rh
https://keras.io/examples/vision/retinanet/ …pic.twitter.com/BNMWNV3gx1
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks a lot!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It seems like keras is doing great job for beginners recently.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Do you have a detr implementation I could look?
-
Here's one, there are a couple more on GitHub it seems... https://github.com/auvisusAI/detr-tensorflow …
- Show replies
New conversation -
-
-
Could someone recomend some maths courses for beginners on deep learning? I'm looking forward to building projects like this one. Cheers!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@srihari_rh Thank you so much for the code, as pointed out by@fchollet it is really concise and clear. I am trying to use your example with a custom dataset (set of .jpg images + annotation .txt files produced with labelImg). Any advice or good references worth investigating?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.