Comments (7)
@chenxiaoyu523 Yes. In the speed experiments, we use the low-scale labels for the fast inference speed, which is mentioned in our paper.
Hi @ycszen! Did you mean you used labels at 1/8 scale to calculate mIoU?
Also could you please kindly point out where did you mention this in your paper?
Thank you very much!
from torchseg.
@lxtGH Based on the setting and pre-trained model, you can reproduce the performance. Now, because our repo contains both distributed-training method and non-distributed-training method, the setting may be a little confused. I will abandon the non-distributed-training method and give a pure distributed training setting for reproduction and make the pre-trained models available in the next version.
from torchseg.
The same question. How to reproduce your results using resent18 (78 mIoU).
from torchseg.
@chenxiaoyu523 Yes. In the speed experiments, we use the low-scale labels for the fast inference speed, which is mentioned in our paper.
from torchseg.
@chenxiaoyu523 Can you please provide details about the settings used to reproduce the 74 miou result on cityscapes with bisenet.r18.speed?
from torchseg.
@cpapaionn i guess you changed the batch_size in config.py. i tested the code on different settings of batch_size and get miou 68 on batch_size 4, 72 on 8 and 74.8 on 16. If you have only one display card, you can try this: https://discuss.pytorch.org/t/how-to-implement-accumulated-gradient-in-pytorch-i-e-iter-size-in-caffe-prototxt/2522
from torchseg.
@chenxiaoyu523 yes I did change the batch size to 4 as I only used a single gpu, I 'll try this, thank you very much!!
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.