-
I was trying to convert my tiny-yolov4 darknet weight into ONNX format. When I run `python demo_darknet2onnx.py ` by replacing each values. I got 2 ONNX model file:
- yolov4_1_3_416_416_static.on…
-
Fail to convert tiny version, any help for it? thanks
-
Hi!
I am currently going back and forth between this repository and your other repository [PyTorch_YOLOv4](https://github.com/WongKinYiu/PyTorch_YOLOv4).
I am a bit confused as to how your tiny conf…
-
Hi, thanks for your wonderful work. However, I have got very different results from cpu and edgetpu. In the following image, left one is the result using cpu, and the right one is the result using edg…
-
For speed up of detection, i tried yolov3-tiny model. But it causes a panic. can i used it?
-
I am using yolov4-tiny.weights with yolov4-tiny-relu-new_coords.cfg and using yolov4-tiny-relu-new_coords-tpu.cfg convert to tflite with compile.
But the perform on the edgetpu is 60sec per image. …
-
Hello here, I hope someone can help me, thanks in advance.
This is my development environment :
- Ubuntu 20.04 (VirtualBox, 3CPU)
- OpenCV 4.2.0
- Tensorflow 2.3.0rc0
When i run : python2 sav…
-
I have changed the cfg for the correct number of classes, filters, max batches, and steps
in the yolo loss function I have changed:
- image_size = 416
- self.strides = [32, 16]
- self.anchors…
-
大佬，有什么建议将yolov-4转为caffe吗，现在卡到了通道数减半这个操作上，caffe有哪个对应层可以对应吗，或者几个层组合实现这个功能，非常感谢
-
Hello,
I am using the tiny variants of YOLO on darknet_ros [https://github.com/tom13133/darknet_ros.git]. It seems that on all of them I am getting around 0.9-1.1 FPS on just CPU (core i7 if that is …