-
I trained a custom model with yolov4-tiny-3l and yolov7-tiny - both using the same hyper parameter(flip, disabled mixup, disabled ota) and the same dataset. Also both were trained by starting from pre…
-
Hey,
The inferences of my model only show the name of the Class but not the confidence. Confidence for me is neither displayed anywhere.
From Yolov5, YoloR etc. confidence was always in the pi…
-
作者你好,使用scaled yolov4
还可以像V5 一样 将背景类别,无标签的空图片,放到训练中吗,检测标签的时候报了这个 assert labrels >5 错误,
Hello author, using scaled yolov4
Can you still put the background category and the empty picture withou…
-
**Describe the bug**
Darknet built successfully.
The issue occurs when testing the repo with the sample:
```
go build main.go && ./main --configFile=../yolov4.cfg --weightsFile=../yolov4.weights -…
-
Hi,
I am getting "cuda out of memory" error for yolov4 training with coco2017 datasets
my cfg is:
1 [net]
2 batch=64
3 subdivisions=32
4 # Training
5 width=416
6 height=416
…
-
-
测试环境:Ubuntu16.04, RTX2080Ti(11G),TensorRT-6.0.1.5, Cuda 10.0, Cudnn 7.6.1;
YoloV4 模型为:512*512 tiny模型, 7类;
同时剪层和通道,shortcuts 12 ,global_percent 0.5,迭代300次后进行模型微调训练,模型大小也由原来的23.6M降为了8.6M,但是处理耗时基本没变。…
-
### Description
### Problem
I am trying to run yolov4-tiny on the edge TPU, but found out that when the model is ran on the edge TPU, it produces a very different output compared to the CPU. Using…
-
I wanna utilize darknet.py to use yolov4 in my python project.
however after build the darknet and write down my script there is an error shown below.
`OSError: ./libdarknet.so: cannot open shared…
-
I'm integrating in Pyqt gui. python detect_video.py --weights ./checkpoints/custom-416 --size 416 --model yolov4 --video 0 I want to run without cmd