Hyeonki Hong

TF 2 is not yet stable. Depending on the version, it may or may not be converted. A high version doesn't mean it works.

In my test, Add, Sub, and Mul are each supported, but if there are more than three(? or four) consecutive operations, the parts are not converted. ```shell Model: "YOLOv4Tiny" _________________________________________________________________...

> I've been doing lots of tests also with yolov4-tiny on Google Coral and the best solution is to split the model in two: > > * Darknet and Features...

@tgx-lim [yolov4-tiny-relu.weights](https://drive.google.com/file/d/125peB0v697OSh_qN44WdM2MV3mTR56oi/view?usp=sharing) Since model is being trained, the mAP score is still below expectations. ```python from yolov4.tf import YOLOv4 yolo = YOLOv4(tiny=True) yolo.classes = "dataset/coco.names" yolo.make_model(activation1="relu") yolo.load_weights("yolov4-tiny-relu.weights", weights_type="yolo") yolo.inference("image.png") ```...

@ankandrew I'm not sure what's better. I'll try relu6 after finishing relu test. :)

On my test yolov4-tiny-relu with head(224x224) 21ms ~ yolov4-tiny-relu with head(608x608) 132ms ~ I think this model can speed up by finding a few optimization methods, but is there any...

I compiled the tflite with -a. ```shell $ edgetpu_compiler -a yolov4-tiny-relu-int8.tflite Edge TPU Compiler version 15.0.340273435 Model compiled successfully in 1105 ms. Input model: yolov4-tiny-relu-int8.tflite Input size: 5.96MiB Output model:...

What model did you use? And can you share your script?

I don't know what is pred. `yolo.inference()` has no return and `yolo.predict()` return `pred_bboxes == Dim(-1, (x, y, w, h, class_id, probability))` If you want (1,19,19,x) shape, use `yolo.model.predict()`

And ref: https://github.com/hhk7734/tensorflow-yolov4/issues/23#issuecomment-687859586 To speed up, I'll test it out ASAP.