Comments (8)
Compared with the official, there are some optimizations, and the training method adopts the parameter configuration of yolov5
from yoloair.
Compared with the official, there are some optimizations, and the training method adopts the parameter configuration of yolov5
对比了下,本仓库的YOLOX-S参数量约为8.0M,官方YOLOX-S参数量是8.9M,请问是改变了什么模块吗?只是超参数的调整不应该参数量不一致吧
from yoloair.
用自己的数据集训练本仓库的YOLOX-S比官方YOLOX-S要高6-7个点,本仓库YOLOX代码和官方YOLOX代码哪里不一样吗?
你好,请问你是怎么训练的yolox呢?这个存储库不是yolov5的嘛
from yoloair.
用自己的数据集训练本仓库的YOLOX-S比官方YOLOX-S要高6-7个点,本仓库YOLOX代码和官方YOLOX代码哪里不一样吗?
你好,请问你是怎么训练的yolox呢?这个存储库不是yolov5的嘛
仓库里,configs文件夹里有yolox的网络结构
from yoloair.
嗯嗯,看到了,所以我想用这个存储库的yolox进行训练的话,把这个命令:
python path/to/train.py --data coco128.yaml --weights '' --cfg yolov5s.yaml --img 640
改成:
python path/to/train.py --data coco128.yaml --weights '' --cfg yolox.yaml --img 640
就可以了嘛
from yoloair.
嗯嗯,看到了,所以我想用这个存储库的yolox进行训练的话,把这个命令:
python path/to/train.py --data coco128.yaml --weights '' --cfg yolov5s.yaml --img 640
改成:python path/to/train.py --data coco128.yaml --weights '' --cfg yolox.yaml --img 640
就可以了嘛
中间可能会报一些错误,根据错误修改就跑通了,在issue可以查找解决办法
from yoloair.
好的,感谢~
from yoloair.
请问,在训练yolox的时候,训练到一定epoch时,发生报错:
assertion input_val zero && input_val one cuda trigger
RuntimeError: CUDA error: device-side assert triggered
怎么解决呢?
感谢大佬们解答!
from yoloair.
Related Issues (20)
- YOLOE
- PPYOLO
- yolov7-swin-transformer
- python train.py --data slide.yaml --cfg configs/transformer/yolov5s_swinv2_head.yaml
- When training YOLOX, val / box _ loss, val / obj _ loss and val / cls _ loss are always 0, why is this ? How to solve ? HOT 1
- 热力图 HOT 1
- I have a question in yolov5_p2.yaml
- How to output model size information?
- 你好,我在yolov5 7.0版本添加了yolox的代码,现在的情况是cls loss不断上涨,导致map一直为0没有结果,请问这个库可以跟随官方更新至最新的7.0版本吗 HOT 1
- RuntimeError: There were no tensor arguments to this function
- When will the code for yolov8 be added?
- some attention modules do not exist
- UnicodeDecodeError: 'gbk' codec can't decode byte 0xb6 in position 1904: illegal multibyte sequence YOLO air HOT 2
- how to export from 'pt' format to 'onnx' format and use Tensor to accelerate detection
- C3STR issue?
- NameError: name 'DetectX' is not defined
- 可以实现yolov8中的c2f+Swim Transformer吗
- ModuleNotFoundError: No module named 'models.Core2024.EMO' HOT 5
- models.Core2024.EMO HOT 1
- No module named 'models.Core2024.EMO' HOT 2
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 yoloair.