Comments (7)
Turns out, the loss function was grossly incorrect. It needed a K.cumsum for the y_true and y_pred. This is the reason the vast majority of the images give extremely similar scores in the 4.7x to 5.3x range.
I'm retraining the network, which will take 16 hours for 10 epochs. Hopefully the results are much better this time around.
from neural-image-assessment.
Yes this is most likely due to insufficient training. I only trained for 10 epochs on the AVA dataset, whereas they recommend a few hundred epochs. That isnt possibly for me since it takes roughly 1.3 hours per epoch on my laptop.
from neural-image-assessment.
thanks for your jobs!
I want to know that if your training data is all the ava images or part of it?
The total number of ava images is 255530,has you train for all of them?
from neural-image-assessment.
I'm training on the first 250,000 images, and validating on the remaining 5000~ images. I don't think the nima paper gave a clear validation set.
from neural-image-assessment.
HI
How can I get the Ava dataset?
from neural-image-assessment.
@aijianiula0601 Please search on Google.
from neural-image-assessment.
Just pushed a commit with the updated weights (trained from scratch on the fix #2).
Turns out, there is a small error in the calculation (cause it does it batchwise directly rather than batch of samples, thereby the losses are slightly higher than expected). Therefore this model is being further finetuned for 10 more epochs on this loss from #3
from neural-image-assessment.
Related Issues (20)
- when i train model on TID2013 dataset,something went wrong HOT 8
- Weight freezing in train*.py HOT 2
- I've computed histograms of the ground truth and predicted scores HOT 5
- Can't instantiate abstract class DatasetV1 with abstract methods _as_variant_tensor, _inputs HOT 5
- Regarding results
- How to set arguments: HOT 1
- Tensorflow version Issue HOT 1
- Different results
- errors when i run extract_inception_features.py HOT 7
- parse data function-image augmentation HOT 4
- A fundamental question! HOT 6
- Theano backend HOT 3
- License?
- any install instructions ? HOT 1
- How to feed the y_labels or scores from the images to model?
- Van Gogh's Mona Lisa is only 4.266 points??? HOT 1
- Nasnet weights? HOT 1
- Performance issues in the program HOT 2
- Performance issues in utils/data_loader.py (by P3) HOT 1
- Dataset format 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 neural-image-assessment.