Comments (7)
caffe's load_image seems to return floats in the range 0-1.0, while the library usually expects uint8 in the range 0-255. So you would have to do something like (img*255).astype(np.uint8)
after loading the images.
Considering your image size of 32x32, the number of augmenters is also rather large. You should probably decrease each augmenters probability by changing st = lambda aug: iaa.Sometimes(0.3, aug)
to st = lambda aug: iaa.Sometimes(0.1, aug)
.
Further, you should use something like seq.show_grid(images[0], rows=8, cols=8)
to show your augmenters results instead of plt.imshow(images_aug[0])
, as the latter one will result in the same augmentation at every script run.
from imgaug.
I meant a command line program see
, not a pypi package with that name, i.e. you must be able to type see
in the command line and not get an error (that's how I understood it from the help threads - the program seems to be available on Ubuntu by default).
from imgaug.
OK, I ran some more tests individually on each of those options, it seems onlyiaa.Fliplr(0.5)
and iaa.Flipud(0.5)
work. the rest result in a black image which I posted above!
What am I missing here?!
(By the way I'm on windows10
.)
from imgaug.
@aleju : Thank you very much. The black image issue is gone.
and speaking of seg.show_grid(), it fails for me with this error RuntimeError: Could not execute image viewer.
I could'nt find a way to solve it, I have no idea whats causing this! so thats why I used the plt.imshow instead
from imgaug.
The threads that I can find sound like the command see
must be available for misc.imshow to work (or an image viewer must be set in the environment variable SCIPY_PIL_IMAGE_VIEWER
). I guess that command isn't available in Windows 10. Maybe I'll switch to OpenCV's imshow equivalent.
from imgaug.
I installed see
through pip
yet I still get the same error.
from imgaug.
how to install the see program over mac os
from imgaug.
Related Issues (20)
- Project dependencies may have API risk issues
- Is this project abandoned? HOT 8
- how to use imgaug to aug single image just one time?
- Out Of Memory (OOM) error in perspective transformation
- Support for Oriented Bouding Boxes
- AttributeError: module 'imgaug.augmenters' has no attribute 'LinearmnContrast' HOT 1
- numpy 1.20 bool deprecation HOT 1
- AttributeError: 'FigureCanvasAgg' object has no attribute 'set_window_title' HOT 2
- PIL version leads to immutable error
- It doesnt support latestversion of numpy HOT 2
- Track Random Augmentations as They Are Applied
- how to generate such image effect from clear images? I want to simulate scanner effects
- ImportError: cannot import name 'QhullError' from 'scipy.spatial' (/opt/conda/lib/python3.10/site-packages/scipy/spatial/__init__.py) HOT 3
- [BUG] show_grid and draw_grid are incompatible
- AttributeError: 'Delaunay' object has no attribute 'vertices'
- Affine transformation with warp mode doesn't "roll" keypoints
- "Fliplr" I am not sure what is wrong with this operation,
- "Fliplr", after applying this operation labels got disturbed
- Augment only parts of the image
- Adding BlendAlphaSimplexNoise into an augmentation sequence fails to convert keypoints
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 imgaug.