Closed AlexeyAB closed 4 years ago
@AlexeyAB Hey~! Hi :sunglasses:
hunglc007/tensorflow-yolov4-tflite has some problems with training. After solving this problem, I will manage BoF functions.
Then, I try to add YOLOv4-tiny. Thanks for letting me know.
@hhk7734 Hi,
hunglc007/tensorflow-yolov4-tflite has some problems with training.
Did you solve this issue?
Also how many FPS did you get for YOLO4-tiny on Coral board(TPU)? https://github.com/hhk7734/tensorflow-yolov4#objective
CIoU
Tiny
Mosaic
Requests were reflected. :)
@hhk7734 Great!
Do you know the reason? https://github.com/hunglc007/tensorflow-yolov4-tflite/issues/165
I studied artificial intelligence since May. So there are many things that I do not know.
@hhk7734 Very interesting to see v4 tiny on Edge TPU. I have two questions
Thanks
@hhk7734 Hi, Nice work with pypi: https://pypi.org/project/yolov4/
Did you manage to realize CIoU-loss and Mosaic?
Also YOLOv4-tiny is released:
There is required only 1 feature:
groups=
andgroup_id=
to the[route]
layer.So if input is
WxHxC
, it divides input into 2 groupsWxHx(C/2)
(there are 2 groups: 0 and 1), and loads the 2nd group_1WxHx(C/2)
.If there are many layers specified in
layers=
parameter, then this will be done for each of the input layers specified inlayer=
, then results will be concatenated across channels.