Comments (10)
And I don't calculate the weights of classes because the data just has two classes, building and no_building. I want to know that if it is necessary to calculate the weights.
from hyperseg.
I found the same problems also appear when I train the model on data CamVid.
from hyperseg.
have you solved this problem? I met the same problem before the Original Traceback.
from hyperseg.
I think maybe because of the version of your environment. I have solved this problem after I changed my environment.
from hyperseg.
Thank you for your answer, but my code can run on another dataset. So I checked the current data set. Unfortunately, no problems were found.
It is strange that my original trace gave me the wrong code that had been run before and had no problems.Do you know why?
from hyperseg.
Is the dataset you tried successfully given by the author? Or your own? And what about the dataset you cannot run?
from hyperseg.
Thank you for your advice.It is truly the problem of my data set.I download my data set on GitHub and find that it is different from the official data set
from hyperseg.
I use the dataset given by author. But the bug still occurs. I don't understand change what version of environment. Could you tell me more detail of your solution?
from hyperseg.
I fixed this issue and added an exact environment installation yml.
from hyperseg.
Related Issues (20)
- The difference between the Resize(512, 1024) and LargerEdgeResize(512, 1024) HOT 1
- how to test the model on custom dataset? HOT 1
- How to output the image of the segmented result? HOT 1
- How to convert the pth file to onnx?
- Please consider the citation
- Backbone HOT 1
- Inference HOT 1
- ModuleNotFoundError:No module named ‘hyperseg’ HOT 5
- signal_index is not getting updated HOT 1
- hyperseg
- Assertion `t >= 0 && t < n_classes` failed. HOT 3
- About Test bug HOT 2
- Another bug about the script of train camvid HOT 2
- I don't find predict.py
- Error in operation camvid_efficientnet_b1_hyperseg-s HOT 2
- unknown resampling filter (InterpolationMode.BICUBIC). HOT 2
- RuntimeError: CUDA error: device-side assert triggered HOT 1
- inference hflip
- Hi,please help me, 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 hyperseg.