Comments (3)
If this is not possible, a workaround could be achieved if albumentation returns me the "perceived" visibility after the transformation. In that way I could calculate the "real" visibility as the multiplication of the initial and the perceived visibilities.
from albumentations.
I do not understand the question yet.
As I understand, you crop parts from the image and bounding boxes that are not 100% contained in the image get truncated, right? And this becomes an issue.
Or not?
Could you provide some code?
from albumentations.
Hi @ternaus , thanks for the reply.
Yes, you are correct. They get truncated. Therefore their visibility is not 100% to start with.
Unfortunately I don't think providing code will make things any clearer, because this is more of an workflow problem. So let me give an hypothetical situation:
1 - Imagine my dataset have images 2000x2000 px.
2 - My model just works with images of 500x500.
3 - Since I need the full resolution to identify the objects, I should not shrink the images. What I do instead is to slice the full res image (2000x2000) into 16 non-overlapping 500x500 patches.
4 - Now, imagine that there is a 2000x2000 image with two objects. During the slicing process, one object gets cut in half. The other stays fully visible in a single patch.
Everything up to this point happens before training the model. Its dataset pre-processing and has nothing to do with Albumentations.
5 - Now I'll start training a model and use albumentations. Then comes the question: Given that I want to work with minimal visibility of 40%, which value of min_visibility
should I give to albumentations?
- If I use 40%, the object that was cut in half may end up being only 20% visible (40% of 50%)
- If I use a higher value, that would be too conservative for the object that stayed fully visible.
from albumentations.
Related Issues (20)
- [Documentation] Clean up always_apply from docs HOT 1
- [Documentation] Add to documentation about HFHub load / save functionality HOT 1
- Targets that should be ignored HOT 10
- [Feature Request] Add Text Transform HOT 2
- Optional version update check on library import HOT 1
- Huggingface demo link in docs does not allow user uploaded images HOT 2
- Instance Segmentation Mask/Bbox Relation HOT 2
- opencv-python-headless continues to be installed despite meeting MIN_OPENCV_VERSION with opencv-python HOT 7
- [Bug] When applying `return_params=True` in Compose, it does not return class names, butintegers, instead
- [Feature request] Add balanced scale to `Affine`
- Request: ability to reject augmented images
- AttributeError: 'Albumentations' object has no attribute 'contains_spatial' HOT 2
- GaussNoise broken in 1.4.9 HOT 12
- Can't do any data augmentation on my custom dataset in FiftyOne HOT 1
- Environmental variables to disable auto-update seems to be NO_ALBUMENTATIONS_UPDATE but is documented as ALBUMENTATIONS_NO_AUTO_UPDATE HOT 1
- [Benchmark] Add Augmentor to bechmark
- [Bug] Bug in RandomCropNearBBox HOT 1
- Fix available keys
- [it may be a bug but I am not sure] rotating and cropping adding in pixels HOT 4
- keypoint position shifting during image rotation HOT 3
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 albumentations.