Comments (9)
@zhu-zhu-ding 我们训练时的isprs potsdam数据集不是拿mmseg制作的,参见以下issue:
ViTAE-Transformer/ViTAE-Transformer-Remote-Sensing#21
ViTAE-Transformer/ViTAE-Transformer-Remote-Sensing#23
ViTAE-Transformer/ViTAE-Transformer-Remote-Sensing#27
ViTAE-Transformer/ViTAE-Transformer-Remote-Sensing#9
from remote-sensing-rvsa.
根据作者你提供的修改方式修改了config和dataset,并且数据和你使用的一样,但是报这个错误,请问是什么导致的呢,非常感谢!
from remote-sensing-rvsa.
@zhu-zhu-ding 标签不对吧,还有类别数相关的设置
from remote-sensing-rvsa.
我都是用作者你RSP仓库里的那个转换代码,感觉没什么问题,不知道是那个参数设置的不对,所以可能是我的数据集下载错了吗还是其他什么原因?我用mmseg官方文档的链接下的,感觉都没问题。。。
from remote-sensing-rvsa.
哦还有个问题,
这个num_class设置=5会报错,提示未知参数,这个的错误原因是什么呢
from remote-sensing-rvsa.
@zhu-zhu-ding 有问题啊,你说的那个RSP仓库里的标签转换工具那是mmseg自带的,我没用,我用的是我们之前做项目时候的标签转换方案,在这个issue中,我给了我们转换potsdam数据集的代码,你把这个issue从头到尾完整看完就明白了
ViTAE-Transformer/ViTAE-Transformer-Remote-Sensing#9
from remote-sensing-rvsa.
我看完了,我理解了整个流程,但是问题在于,我使用官方的转换代码,reduce_zero_label和ignore_index按issues修改,但是还是有如上错误,请问这是怎么回事呢?
from remote-sensing-rvsa.
说明customdataset这个类里边没有num_classes这个参数,因为这个参数是设置模型输出类别个数的,只在模型config里边的head上设置就可以了
from remote-sensing-rvsa.
@zhu-zhu-ding 你这个错误肯定跟标签有关,所以你要注意的地方应该有,数据集类里的ignore_index, 数据集config里边pipeline中的reduce_zero_label, seg_pad_val, 模型config里边decode_head和auxiliary_head中的num_classes和ignore_index
from remote-sensing-rvsa.
Related Issues (20)
- 代码中value角度变换问题 HOT 1
- mmcv版本问题 HOT 11
- Problem:MillionAID dataset HOT 1
- I reproduced the code with an accuracy of only 54 HOT 19
- KeyError: 'OrientedRCNN is not in the models registry' HOT 3
- LoveDA dataset training proble HOT 1
- Questions about labels for the MillionAID dataset HOT 1
- Pretrained Model Weights HOT 2
- Model pth HOT 3
- Missing script: tools/test.py file missing for segmentation and detection HOT 2
- 预训练模型 HOT 1
- 图片大小不一样 HOT 1
- 推理得到的结果如何计算mIou指标 HOT 6
- [resume error] loaded state dict has a different number of parameter groups HOT 3
- 预训练模型 HOT 2
- 目标检测识别任务的训练评估结果复现不成功。能够成功复现obbdetection仓库oriented_rcnn的训练评估结果,但vitae-rvsa_dota10_ms的训练评估效果不理想 HOT 3
- Unable to download pretrained checkpoints
- potsdam_vitae_rvsa_kvidff权重推理时的精度差异 HOT 4
- ViTAE_NC_Win_RVSA_V3_WSZ7预训练权重加载 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 remote-sensing-rvsa.