Comments (7)
You need to put the pre-trained weight under the corresponding folder.
from segnext.
You need to put the pre-trained weight under the corresponding folder.
And You need to load the pre-trained weight by changing local_configs/segnext/base/segnext.base.512x512.tusimple.160k.py like other configs.
from segnext.
i change the weight's path in code of' local_configs/segnext/base/segnext.base.512x512.tusimple.160k.py' like the first picture,
but when i train my dataset, the result is showed like the second picture , is very Irregular. emmm, thank you very much for bothering you for my question !
from segnext.
my data has only 2 classes(background and road_line), in my opinion, the dataset_config should be correct! thanks very much.
from segnext.
If you modify your dataset according to ade20k, you may ignore the label 0.
from segnext.
ooo, thanks, maybe this is a cause, but if i need to consider the background based the dataset ade20k, and i can modify where code ?
from segnext.
thanks i have found the error and it has been trained normally, the reduce_zero_label should be False in my dataset config
from segnext.
Related Issues (20)
- Welcome update to OpenMMLab 2.0
- Inconsistencies in ADE20K model inference output for the same input image. HOT 3
- How to start training? HOT 1
- AssertionError: train_cfg specified in both outer field and model field
- Comparison with SegFormer-B5 HOT 1
- ImportError: cannot import name 'revert_sync_batchnorm' from 'mmcv.cnn.utils' HOT 1
- Training gpu consumption vs inference gpu consumption
- about AttentionModule
- If I want to train with 4 GPUs, do I need to change the code
- Evaluation Result on Cityscapes
- How to stop shuffle for test.py
- Config file for the i-SAID dataset
- Can you provide the IOU per class of IsAID dataset?
- 大佬们你们下载的哪个版本的mmcv 为什么我版本较老(mmcv-full1.6.0) 会报错 版本太新(mmcv r4)没有mmcv.runner? HOT 2
- mIoU and MPA
- 随机性问题
- reproduce official results
- 对于SegNext模型,我发现每次的测试结果都不同,这是为什么?
- 对于SegNext模型,我发现每次的测试结果都不同,这是为什么?
- 模型讲解
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 segnext.