Comments (10)
Compared to the original deeplabv2 paper, two things were not implemented:
- MSC: Employing mutli-scale inputs with max fusion.
- CRF
My mIoU on val is 75.1, which is reasonable.
from deeplab-v2--resnet-101--tensorflow.
Hello, I just run your code on augmented pascalvoc datasets, and not change anything.
After iter 20000, I test just get mIoU 68.8%, do you know why? Thanks!
from deeplab-v2--resnet-101--tensorflow.
And more, the loss just shocks, after iter 20000, the final loss is aroud 1.3.
from deeplab-v2--resnet-101--tensorflow.
Which pre-trained model did you use?
from deeplab-v2--resnet-101--tensorflow.
And you may notice that you need to change 'valid_step' in main.py for testing/validation.
from deeplab-v2--resnet-101--tensorflow.
I use deeplab_resnet_init.ckpt as my pertained model,and valid step is changed to 20000.
from deeplab-v2--resnet-101--tensorflow.
Your final loss is correct. I cannot figure out what happened in your case without more information. I tested the code for several runs, the mIoU results for val are consistently around 75.
from deeplab-v2--resnet-101--tensorflow.
@dyz-zju 您好,我也只跑出了0.68,请问后来您的结果怎么样了
from deeplab-v2--resnet-101--tensorflow.
Please check #7
from deeplab-v2--resnet-101--tensorflow.
@CaiziLee you need to use another dataset processed by author, the url can be found in somewhere.
from deeplab-v2--resnet-101--tensorflow.
Related Issues (20)
- Optimizer choice: Adam VS SGD HOT 1
- Another dataset HOT 4
- Problem with pre-trained model HOT 1
- Results for VOC2012 are not correct HOT 3
- Training Cityscapes - Changes in label_utils.py HOT 1
- pretrain model download
- How to process the outline of the object in Segmentation label images? HOT 1
- The problem about paper "Smoothed Dilated Convolutions for Improved Dense Prediction". HOT 1
- Which part of your code corresponds to the CRF in Deeplab V2? HOT 1
- How to predict dynamically from graph HOT 1
- A question about paper "Smoothed Dilated Convolutions for Improved Dense Prediction" HOT 2
- NotFoundError (see above for traceback): Tensor name HOT 3
- only can train 2images HOT 1
- Can I input 6 channel images for training? HOT 2
- how about results(mIoU) on validation set and test set HOT 2
- Hi, could you please implement it on cityscape? HOT 3
- how about the hyperparms of cityscape
- ABOUT BATCHSIZE WHEN TRAINING ON CITYSCAPES HOT 1
- It is OOM. Try reducing input_height and input_width. HOT 1
- resnet101 ------- miou 70.7% HOT 2
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 deeplab-v2--resnet-101--tensorflow.