Comments (20)
Personally I think you should use OHEM loss for training which his paper didn't mention.
from torchseg.
I get a similar mean IoU 69.688% with R18. I train the model from scratch because the pretrained R18 model is not released. Can you share the pretrained model?
from torchseg.
Personally I think you should use OHEM loss for training which his paper didn't mention.
Thank you but I've already utilized OHEM.
from torchseg.
Maybe you can try large cropsize
from torchseg.
@msc-rajesh Which experiments did you use, cityscapes.bisenet.R18.speed
or cityscapes.bisenet.R18
? I will re-run it to check the performance.
from torchseg.
@ycszen I run cityscapes.bisenet.R18 with one GPU. I get mean IoU 69.688%.
from torchseg.
@daodaofr I have re-run the cityscapes.bisenet.R18
experiment. The performance is normal. I run this experiment on 4 GPUs. Besides, I think maybe you train from scratch resulting in the performance drop. You can load the official R18 model in Pytorch before I release the pre-trained model.
from torchseg.
@daodaofr : I ran cityscape.bisenet.R18 experiment on 4 GPU's having product name NVidia GeForce GTX 1080 Ti.
I have trained BiSeNet from scratch on CityScape leftImg8bit folder (used "labelTrainIds" instead of "labelIds" from gtFine folder for GT's) with train input image dimensions 1024x1024.
I got mean IoU value 70.446% on validation folder of the CityScape dataset.
from torchseg.
@ycszen @ms-krajesh
I run the model from official R18 model in Pytorch, and I got 72.753% mean IoU.
I think gap is from the pretrained model.
from torchseg.
@daodaofr : Did you used "labelTrainIds" or "labelIds" for GT's?
from torchseg.
@ms-krajesh I used labelIds
from torchseg.
@daodaofr but the class number in labelids is 33, which is not corresponding with the code, do you have any other processes?
from torchseg.
@chenxiaoyu523 Yes, I set the label of invalid classes to ignore_index.
from torchseg.
@ycszen I run your R18.speed and R18 with 4 1080Ti. the accuracies for last epoch models are 74.2 and 75.2. which is a little bit less than your reported accuracy (74.6 and 76.3). Where should be the problem? shall I check the acc for each epoch?
from torchseg.
Can someone upload a pretrained model please ?
from torchseg.
I can't get the right result, and the loss not converge with Bisenet. I don't know why ,can you give me some Suggest
from torchseg.
@jiaxue1993 Maybe you can evaluate the models of the last ten epochs.
from torchseg.
@alexanderfrey The pre-trained models have released except the Xception39.
from torchseg.
@haitaobiyao Could you give more details.
from torchseg.
Hi!, I download the pretrained model(R18)and train model from the link you provided,but I am only able to get mean IoU: 65.2% ,Is there any problem with the parameter setting?
from torchseg.
Related Issues (20)
- train a dfn-voc network with my own data HOT 1
- 关于cityscapes.bisenet.R18.speed中下采样label HOT 1
- subprocess.CalledProcessError
- example about the train.txt, val.txt, test.txt
- A exception occurred during Engine initialization, give up running process HOT 1
- about aux_label
- C++
- 关于您提供的BiSeNet_Xception39的复现结果mIOU低
- Inference on my own images HOT 1
- Setting gt_down_sample=1 resulting in reduction of validation accuracy by 4.9% HOT 1
- Where are train.py and eval.py? HOT 1
- Does the .pth file downloaded in google drive need to be retrained?
- The loss calculation of PSPNet
- BiSeNetV2 support
- Training Parameter - Large dataset
- Difference between realtime res18 and non-realtime res18 model HOT 1
- About the pretrained model
- ModuleNotFoundError: No module named 'utils.pyt_utils' HOT 3
- 训练问题
- valueError invalid literal for int() with base10:‘’
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 torchseg.