Comments (6)
你用的paddle还是作者这个版本呢?
from ppyoloe_pytorch.
需要几个点才能达到43.1的精度哦。
1、要8卡机器,并且要达到paddle版本中的batchsize。
2、使用imagenet的预训练权重。(目前的代码其实暂未支持加载imagenet预训练模型,需要自己手动改下代码)
from ppyoloe_pytorch.
你用的paddle还是作者这个版本呢?
是作者这个版本
from ppyoloe_pytorch.
需要几个点才能达到43.1的精度哦。 1、要8卡机器,并且要达到paddle版本中的batchsize。 2、使用imagenet的预训练权重。(目前的代码其实暂未支持加载imagenet预训练模型,需要自己手动改下代码)
好的,我试试
from ppyoloe_pytorch.
其实从这个精度看。没有达到yolox的精度。我记得yolox也是从0开始训练的,没有预训练
通过git上给的命令,我在COCO上训练PPYOLOE-s到300epoch mAP大约38.5%, 到350为40.5%,无法达到43.1%,请问如何训练到paper中的精度。
从这个看,精度达不到yolox的精度。网上150epoch可以达到39.7,论文作者是300epoch40.5.可能与数据增强有点关系吧。下次我自己也试试增加数据增强。有机会大家相互分享一下经验、结果!谢谢
from ppyoloe_pytorch.
需要几个点才能达到43.1的精度哦。 1、要8卡机器,并且要达到paddle版本中的batchsize。 2、使用imagenet的预训练权重。(目前的代码其实暂未支持加载imagenet预训练模型,需要自己手动改下代码)
好的,我试试
你好,请问你复现出来了吗?我在没有预训练模型的情况下ppyoloe_s只能到40.5%左右,ppyoloe_s的cspresnet预训练模型在哪找啊?
from ppyoloe_pytorch.
Related Issues (20)
- ModuleNotFoundError: No module named 'yolox' HOT 1
- 您使用的pytorch版本是多少? HOT 5
- 将paddle转pytorch模型出现的错误,多谢 HOT 1
- 为什么按照指导转的pth,推理就出现了错误? HOT 4
- cocoeval花的时间变长了 HOT 2
- 转成ONNX,并没有做重参数 HOT 3
- 增加mosaic会进一步提升模型的性能吗
- RuntimeError: torch.nn.functional.binary_cross_entropy and torch.nn.BCELoss are unsafe to autocast. HOT 1
- atss使用的epochs
- is there a mask branch based on PPYOLOE?
- Request: Release Pretrained Backbones on cloud other than Baidu
- 评估结果都是0,不知道什么原因,数据集就是COCO HOT 1
- 训练出来的模型自带后处理嘛?
- What about the V100 Speed when compared to the original implementation?
- 去除rescale alignment metrics
- n error has been caught in function 'launch', process 'MainProcess' (10585), thread 'MainThread' (140021255956288):
- AssertionError: assert img is not None
- 训练ppyoloe
- loading state_dict for PPYOLOE error HOT 1
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 ppyoloe_pytorch.