Two other YOLO v3 implementations, based on multi-backend Keras this time (hope they get converted to tf.keras!): 1 - https://github.com/qqwweee/keras-yolo3/ … (most popular) 2 -https://github.com/experiencor/keras-yolo3 …
-
-
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Finally
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Frankly I still prefer this version - https://github.com/experiencor/keras-yolo3/blob/master/train.py … All you've to do is to change to from tensorflow.keras in the imports
-
It has cleaner code and you can actually interpret and understand the logic of yolos architecture there
End of conversation
New conversation -
-
-
Can’t wait to get Yolo v4 support.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Now we need to go 1 step deeper, to detect face with a mask and still able to do facial recognition.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Abbey Road !!! Well, huh… no. Guess I'm not that far from an AI, after all.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Here's my favourite implementation in TF 2.x WITH SUPPORT FOR YOLO v4 with many different backbones, from efficientnet, mobilenetv3, xception, etc. It also provides automation for finding best hooks. Plus, the code is constantly being maintained.https://github.com/david8862/keras-YOLOv3-model-set …
-
Very cool
End of conversation
New conversation -
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.