Comments (5)
Problem with dataset format? You can send me the content of your label .txt
from yolo-fastestv2.
Problem with dataset format? You can send me the content of your label .txt
Thanks for your reply
my one of label.txt, The format is the same as darknet, I am sure it can be used in yolo-fastestv1.1, the effect and speed are very good
0 0.501000 0.501493 0.998000 0.997015
my train.data
[name]
model_name=mosaic
[train-configure]
epochs=300
steps=150,250
batch_size=64
subdivisions=1
learning_rate=0.001
[model-configure]
pre_weights=None
classes=3
width=352
height=352
anchor_num=3
anchors=171.69,262.96, 216.69,174.53, 304.65,205.18, 313.94,300.33, 334.99,259.35, 349.61,347.02
[data-configure]
train=/home/zsf/work/Yolo-FastestV2/train/mosaic/train.txt
val=/home/zsf/work/Yolo-FastestV2/train/mosaic/train.txt
names=/home/zsf/work/Yolo-FastestV2/train/mosaic/classes.names
my train.txt, this is part of it and it can be used correctly in yolo-fastestv1.1
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/black/7.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/black/6.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/black/8.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/black/2.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/black/5.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/black/3.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/black/1.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/black/0.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/black/4.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/blue/7.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/blue/6.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/blue/2.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/blue/5.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/blue/3.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/blue/4.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/mosaic/180.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/mosaic/159.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/mosaic/16.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/mosaic/46.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/mosaic/154.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/mosaic/106.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/mosaic/150.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/mosaic/85.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/mosaic/77.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/mosaic/40.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/mosaic/153.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/mosaic/148.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/mosaic/103.jpg
/home/zsf/work/Yolo-FastestV2/train/mosaic/images/mosaic/133.jpg
my classes.names
mosaic
black
blue
my anchors6.txt
171.69,262.96, 216.69,174.53, 304.65,205.18, 313.94,300.33, 334.99,259.35, 349.61,347.02
0.905269
from yolo-fastestv2.
pytorch version?
from yolo-fastestv2.
Problem with dataset format? You can send me the content of your label .txt
I meet the same error.Some label.txt are empty because these labels correspond to negative samples which have no labels.Could you please tell me how to make my dataset with these negative samples?
from yolo-fastestv2.
Fix it in flyskywhy@0866696
from yolo-fastestv2.
Related Issues (20)
- Why did you choose shufflenetv2 architecture?
- 大佬,如何利用多块gpu进行学习呢? HOT 1
- during training , why precision and ap are all 0?
- android demo
- camera realtime demo HOT 1
- how to train background image without labels?
- 导出onnx后推理结果和pth不同
- train with custom dataset and deploy on raspberry pi4?
- 请问大佬的ncnn对头后处理的模块能用py写一下吗
- 请问多类别训练为什么只能识别到单一类别
- bug
- An error occurred during YOLOX training HOT 1
- 请问怎么调用gpu? HOT 1
- Why the mAP on coco val set (5000 images) is only 0.0242 when I use the coco2017-0.241078ap-model.pth?
- python版本 HOT 1
- 有对应的论文吗
- RuntimeError: result type Float can't be cast to the desired output type long int HOT 3
- 使用ncnn转换之后无法推理
- Python Too Slow Inference Speed, Colab T4 Gpu
- Shufflenet pretrained
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from yolo-fastestv2.