Comments (3)
this also bother me a lot,in most detection task, we don't have the high resolution images. we can not downsample the original image, and then detect. it is more meaningful to contrast the detection result of original images to the detection result of super resolution images
from eesrgan.
For test input, we need only low-resolution images: 4x downsampled with 64 to 64 tile size for the COWC dataset. Then we get super-resolved images with detection.
For testing a new satellite dataset with a resolution around 0.6 m to 1 m, you should create tiles of 64 to 64 size for our architecture. You can also use larger tiles but might need a large GPU memory. With the new tiles, you also need to create corresponding .txt file for the annotations (similar formatting of COWC dataset).
For training a new dataset, you always need a high-low resolution image pairs with ground truth bounding boxes for detection. This architecture support 64 to 64 tiles for training. for example, If you have low-resolution images of 128 to 128 tiles, then you can create 512 to 512 super-resolve tiles. In that case, you need to change the fully connected layer of the discriminator here:
Line 371 in 7aaae20
Thank You.
from eesrgan.
@cl886699 you are right, that is the drawback of super-resolution models. Most of them are trained on images down-sampled from high-resolution images which tend to learn downsampling patterns. So, they don't work on actual low-resolution images.
from eesrgan.
Related Issues (20)
- Can we train to only get Super-Res images? HOT 1
- CUDE out of memory on custom data HOT 3
- about frcnn loss HOT 1
- about the datasets HOT 3
- How to change another detector network HOT 2
- IndexError: list index out of range HOT 5
- RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED
- Train, Validation, Test Split HOT 1
- RuntimeError: A view was created in no_grad mode and is being modified inplace with grad mode enabled. This view is the output of a function that returns multiple views. Such functions do not allow the output views to be modified inplace. You should replace the inplace operation by an out-of-place one HOT 4
- datasets problem HOT 4
- 10000_G.pth HOT 2
- Test Problem HOT 2
- Question about test
- The End-to-End in code HOT 1
- How to train on custom data HOT 2
- torch.jit.frontend.UnsupportedNodeError: JoinedStr aren't supported HOT 1
- About the function 'imresize_np' can't be found in the ''scripts_GAN_HR-LR.py ''
- Some error, when I try losses.backward for train FRCNN HOT 8
- where is the /home/jakaria/Super_Resolution/Filter_Enhance_Detect/saved_ESRGAN/val_images/*/" HOT 1
- ImportError: attempted relative import with no known parent package
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 eesrgan.