Comments (12)
And it appears in almost every result image.
from deblurganv2.
There is a bug in the inference, will be updated soon
from deblurganv2.
Thx for your quick reply, looking forward to the update...
from deblurganv2.
yes,same issue here,has this been solved? I test my images ,purple filled in full image, not only the corner of images, is it this caused by np.transpose function?
from deblurganv2.
so is that caused by the network is not converged?my predict result images were like this
from deblurganv2.
my training images are gray ,I convert them to BGR format,I also remove the hsv,rgb,transform part by changing the config.yaml
the result keep the same ,anywhere maybe lead the problem?By the way I also remove sharpen part,we are bluring the images,why do we need that?I am confused about that
from deblurganv2.
please check the updated links to models (latest changes to readme).
should work fine now
from deblurganv2.
Much thx.
from deblurganv2.
There is still some purple artifact on images with new pre-trained model.
For example:
It seems that relatively dark region/texture prone to have this artifact. When generating video, it trend to have artifact on same object (but not every frames)
Do anyone have idea why this issue happen?
from deblurganv2.
@htleeab Which image in GoPro did you test on and which model did you use? Let me see if i can reproduce that
from deblurganv2.
@Sandbox3aster
Those image are my own test assets, not GoPro dataset. I used the pretrained InceptionResNet-v2 (md5sum: 96f747f38a0119669265cbb5fc7b3c5c)
Thanks.
from deblurganv2.
Same problem here, using cpu and same model
96f747f38a0119669265cbb5fc7b3c5c best_fpn.h5
Ubuntu 18.04.02, python 3.6.9
torch==1.5.0
torchsummary==1.5.1
torchvision==0.6.0
numpy==1.17.4
opencv-python-headless==4.2.0.34
joblib==0.14.0
albumentations==0.4.5
scikit-image==0.17.2
tqdm==4.46.0
tensorboard==2.1.1
fire==0.3.1
Perhaps the newer torch version is acting up?
from deblurganv2.
Related Issues (20)
- Run in Linux error: RuntimeError: cuDNN error: CUDNN_STATUS_BAD_PARAM HOT 1
- How to organize train data?
- Why subsampling buckets
- The points in deblur image are all splited into two
- Is the best model on GOPRO dataset is trained on 256x256 image size or 1280x720 ? HOT 1
- Code fails due to certificate issue with server. HOT 3
- predict.py HOT 3
- how
- how to convert the model to onnx? HOT 3
- url error while running the predict.py ssl certificate error HOT 2
- The command of changing the backbone network
- get the blur estimation value?
- predict.py performs 0 iterations HOT 1
- Certificate issue HOT 4
- I have this problems!win_size exceeds image extent. Either ensure that your images are at least 7x7; HOT 3
- Cannot use predict.py on my dataset
- The imagecolor was changed ? why ? my mistake HOT 1
- Missing Discriminator Weights for pretraining HOT 1
- 模型训练不收敛,loss一直震荡。
- Fixing Security Bugs
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 deblurganv2.