Comments (4)
You can not simply use the pretrained weights, because class definition is totally different for your dataset. The dataloader and dataset class is highly customized for different datasets, you'll definitely need to re-write your own. Perhaps simply changing the number of classes and putting 255 for the rest will fail.
from shelfnet.
When you get nan, clearly something very weird happens. I suggest checking your dataloader and class definition etc first. Seems not a problem with the network, I guess it's the problem with data (e.g. dataloader). Even a quite simple FCN should not generate this type of results.
I'm sorry I might not be able to provide further help, since you are dealing with a private dataset, and I have stopped segmentation projects long time ago.
from shelfnet.
Thank you for the reply.
I did not change the dataloader ,I just used the Indian Driving Dataset images in place of cityscape dataset.
I will look into it.
My only question which remains is that in my case I have only 4 classes,so either I should change the number of classes in the network,but then I doubt if I can use the pretrained weights(because it is trained on 19 classes),or the other hack which I did was to put 255 as the id for all the classes which I need to ignore.
basically I am not sure how to handle different number of classes and classes which the model is not trained on.
Any suggestion is appreciated.
I'm sorry I might not be able to provide further help, since you are dealing with a private dataset, and I have stopped segmentation projects long time ago.
I get it.
Thank you
from shelfnet.
Thanks for the reply!.
I have arranged my data in cityscapes format and hence the dataloader will remain the same right.But I changed the cityscape_config.json to the ids expected by the Indian Driving Dataset.I used 19 classes only this time and using the pretrained weights I still get nan.I expected that after training for a few iterations at least the model should be able to adapt to the new dataset.Most of the classes of the dataset which I am using are the same as that of cityscape,except 2 new classes.But the total number of classes still remains as 19.
from shelfnet.
Related Issues (20)
- Some question about pascal voc test set HOT 1
- 关于arxiv论文 HOT 1
- Compile Errors HOT 5
- pretrained model in google driver untar failed HOT 2
- Can I run the code in one GPU? HOT 4
- C++ Api HOT 1
- Functionality difference between pytorch batchnorm and synchronised batchnorm HOT 3
- TypeError: __init__() got an unexpected keyword argument 'find_unused_parameters' HOT 1
- How to load pretrained weights for training HOT 2
- Tips for better training HOT 2
- RuntimeError: storage has wrong size: expected -4885659930368473377 got 589824 HOT 1
- ImportError: No module named 'inplace_abn' HOT 5
- Which Nvidia GPU card do you use for training? HOT 2
- Get the confidence of the segmented class during test tme HOT 4
- What is the License for this repo? HOT 1
- RuntimeError: ONNX export failed: Couldn't export Python operator InPlaceABNSync
- 关于论文中对Cityscapes的测试结果 HOT 3
- import encoding issue : note: template argument deduction/substitution failed:\nninja: build stopped: subcommand failed.\n" HOT 1
- About data augmentation 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 shelfnet.