Comments (1)
Hi,I have solved this problem,here is my solution:
I used this method(random_color and random_brightness) to do data augmentation during the semantic segmentation,at first I try to augment both the original images.png and the mask.png so that this problem occured
However, the mask.png shouldn't and unnecessary to be augmented because the objects's location and shape and size isn't changed(except rotate and cutout),so that I deleted the codes:
p.ground_truth()
then the codes worked pretty
After that I got the reason why I can't changed the mask.png,due to the reason that the mode of the mask.png is 'L',which means:
mask.mode=='L'
,you can use the code to check it
However,the question is,only the imgs which mode is 'RGB' can be used in the image.py,I don't know why and have no idea to solve it.So,if you faced this problem,here are two ways can be taken into consideration:
1.check your img.mode and make sure they are'RGB' not others,like 'P','L'
2.make sure your imgs are png, this is important.I tryed to use jpg,jpeg in all the methods and all of them have bugs
I hope my advice can help you solve your problem
good luck!
from augmentor.
Related Issues (20)
- How to read and output uint16 images with Augmentor?
- moudle 'Augmentor' has no attribute 'Pipeline'
- int() argument must be a string, a bytes-like object or a number, not 'Image' HOT 4
- why random_erasing sometimes cause error, but sometimes not. HOT 1
- OSError: cannot write mode RGBA as JPEG HOT 2
- What augments should you use?
- label interpolate issue
- p.ground_truth not work for p.add_operation HOT 3
- Not cropping skewed image to original image size HOT 1
- Random Ereasing areas too big HOT 5
- Question - Does it updated the labels too? HOT 3
- Use for Semantic Segmentation HOT 4
- Output dataset format Labelme JSON
- ZeroDivisionError: float division by zero while performing augmentor.sample(num_samples)
- DataPipeline使用sample的时候会报错
- Incompatible with numpy >= 1.20 due to use of type aliases. HOT 1
- Rotation degrees are opposite. HOT 3
- Project dependencies may have API risk issues
- fail to build augmentor 0.2.11 due to a minor typo 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 augmentor.