Comments (5)
Hello, you need your images to be in the 3D shape.
As in not (224,224) but (1,224,224).
Reshaping can resolve your issue.
Other than that as there is a little interest in this project. I will be launching a new code with new features in the next few days.
from contour-detection-pytorch.
@captanlevi Thanks, that helped.
And thanks for letting me know about the new features. I suppose the new features will be added in the same repository, or will there be a new repository for that?
And just one last question about this model. I am getting negative loss values. Do you have any suggestions for this? or is this a normal behavior?
Thanks
from contour-detection-pytorch.
I will work in the same repo, for the negative loss perhaps you have not normalised the images ?
from contour-detection-pytorch.
Yeah, I haven't normalized the images. I am using albumentations for augmentation and I tried to normalize it in the same way. But this didn't help.
Just to clarify, is this how you normalize the images in this code? or I missed that part of code? Because I use the same values for normalization in albumentations but that didn't help me.
Contour-Detection-Pytorch/train.py
Line 101 in e3e6c90
from contour-detection-pytorch.
Okay. I figured it out. Thanks:)
from contour-detection-pytorch.
Related Issues (15)
- the link of the best model can't be opened HOT 1
- Killed: 9 HOT 1
- where is the make_results.py?
- KeyError: 'model_save_path' error HOT 3
- Is it possible to train with data other than pascal data?
- I want "make_result.py" HOT 1
- I want to extract the result file for each image by putting a folder with multiple image files as input HOT 3
- Problem of Q.put HOT 2
- DenseCRF refined segmantation maps for PASCAL-2012 dataset HOT 3
- make_results.py is missing HOT 2
- Segmentation maps for Pascal - 2012? HOT 2
- Constant loss after 5 iterations
- Targets used for the model? HOT 3
- make_results.py 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 contour-detection-pytorch.