Comments (8)
Hi, thank you very much for pointing that out! I'll check that today.
I verified all scores locally so there must be a bug / incorrect snapshot file. Will get back shortly!
from gansformer.
Alright I checked. The source of the issue was a change in the way the dataset images are preprocessed (this line in particular https://github.com/dorarad/gansformer/blob/main/training/misc.py#L137) that caused the images the model is evaluated on to look different than the images it was trained on (using different settings for image ratio and cropping than the original settings used). It should be fixed now, so I recommend rerunning python prepare_data.py --clevr --max-images 100000
to produce the new fixed data and then running the evaluation again on that.
I'm verifying it now too so will be able to follow up in couple hours with a confirmation of whether it resolves the problem.
from gansformer.
Alright, I verified that numbers are now well. Let me know if you still experience the issue.
from gansformer.
Hmm strange, after this my FID reduced to 12.8, but there's still a gap and I can't figure out why...
from gansformer.
Will look further into it!
from gansformer.
Could you send please your md5 hashes of the .tfrecords files as well? So that we could verify whether it's a data issue. Btw samples look just fine
from gansformer.
Yea the issue was just with the data preprocessing (the cropping settings). I'll make the original tfrecords available for download (as is the case currently with FFHQ and Cityscapes) so to ensure perfect match.
from gansformer.
Alright I uploaded the data (the difference between the locally processed data that leads to the FID score 12 is that the images ratio height/weight in the data is 2/3 while the pretrained model was trained on images with ratio 3/4.
You can try again to run python prepare_data.py --clevr --max-images 100000
should take a few minutes only (because will just download the data) and then another 20min to run the
python run_network.py --eval --gpus 0 --expname clevr-exp --dataset clevr --pretrained-pkl gdrive:clevr-snapshot.pkl
. Let me know if you're still getting higher FID!
from gansformer.
Related Issues (20)
- data resolution HOT 2
- AssertionError with prepare_data.py HOT 2
- Data generation HOT 3
- Pretrained Stylegan v2 Model on clevr and cityscapes dataset HOT 1
- Setting up TensorFlow plugin 'fused_bias_act.cu': Loading... Failed! HOT 3
- Memory issue when training 1024 resolution HOT 5
- PyTorch implementation generates same image samples HOT 6
- Pytorch version HOT 1
- Can I use FFHQ 1024 pre-trained model with PyTorch? HOT 1
- GANformer2? HOT 1
- Data Generation
- Can gansformer be used as an image-to-image translation model?
- Ganformer2
- Ganformer2
- Hosting models on Hugging Face
- Training wont work, needs tensor.contrib which was removed in tf version 1.14
- question on duplex attention (k means) code
- FLOPs and #parameters?
- Two typos in pytorch_version/training/loss.py
- Generation of attention maps problem
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 gansformer.