new-yolov1_pytorch's People
Forkers
whgang freedomlyle jcek hlx-d pompeii222 yaojwdefgun phil-chow sihanfei djh-lcx zyzmoonlight leon16226 liufeinuaa sinianyutian wuzuowuyou panyinyin ppx-hub xzltc songh11 liuyundong-2020 mdyuan926 wuxiaolianggit gengjianchun sallyeen chijiujiu zheng-yun xingpanfeng ngoccc 781226451 xiaoyangon xiebinbb cxcx1 lichenglong123 fardman69420 usigned awille hqwdev qiong-14 skro123 spring-long hdm8809 our1314 eversee22 dongyaolin lqwang1025 healthboyy hardcorehenr zhousiyi0107 yuntaoshou jesse01 cosastro dingrizhi ntduong31 chengbo5 flyphoenix456 jo-dean wuweijie0413 lizhengli10086 lychnin tsingachieve war3et darcy0 jasuexiiinew-yolov1_pytorch's Issues
File was loaded in the wrong encoding: 'UTF-8'
The file generated in the folder : "voc_eval" is not available , and the error is File was loaded in the wrong encoding : 'UTF-8' , I've tried every encoding ,but the problem still exist
how can I solve this problem?
thanks!
Sharing Weights on Google Drive
Hi, Can you please share the weights in either Google Drive or Dropbox. It would be really helpful
感谢大佬的教程,代码也很清晰整洁
类别输出未经过softmax层
作者大大你好,感谢你提供的代码,对我帮助很大!
我最近在做三维的目标检测,在修改代码之后发现类别部分的损失出现负数,搜索之后发现这是因为交叉熵损失的输入大于1,而经过检查也确实发现在网络的训练阶段,类别输出好像没有经过softmax层,这样是对的吗?
你这个预测头为什么最后通道数是25?不应该是30么
你这个预测头为什么最后通道数是25?不应该是30么
SAM模块问题
我看了一下原版的论文, 加了CBAM 后代码很多人train效果还不如原版的resnet50。
请问一下作者有没有去掉SAM模块试过呢?效果如何?
Why we should use normalize to the image?
Hi! Thanks for awesome work!
Recently, I am trying to design a new object detection network based on yolov1, my work is based on another work https://github.com/abeardear/pytorch-YOLO-v1/blob/master/train.py . I have tested that my work can overfit in Pascal VOC 2007+2012 trainval. But my work suffered heavy overfit . I have tried dropout weight decay and data augment . But the problem is still not solved. And I noticed your work , I find that you will do a normalize to image which is other work doesn't have . Why you do it? Is is have an advantage in overcoming overfit?
Looking forward to your reply!
请问该怎么在这个代码的基础上将backbone替换为VGG16?
我目前的做法是去掉了VGG16的classifier,然后在yolomodel中将stride改为69,这样标签的维度就变成了6,6,25,但是在预训练的vgg16的基础上,只能跑到58.76,而baseline为66.4,请问我该怎么修改代码得到baseline?
不好意思,将new-YOLOv1_PyTorch与PyTorch_YOLOv1混淆,已issue至对应仓库
init() got an unexpected keyword argument 'mosaic',我自己在所有文件目录下都未找到mosaic
这是yolov1还是yolov2
这是yolov1还是yolov2
This is yolov1? yolov2?
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.