Comments (3)
Try out albumenation resize
from aucmedi.
skimage resize vs albumentations (cv2) resize
Experiment setting:
- Batchsize 32
- No Image Augmentation
- No standardization
- No other subfunctions
Results:
Test: 0 Using: albumentations
Time: 4.971815347671509
Number of Workers: 0
Test: 1 Using: albumentations
Time: 4.843110084533691
Number of Workers: 1
Test: 2 Using: albumentations
Time: 3.4497203826904297
Number of Workers: 2
Test: 3 Using: albumentations
Time: 2.855795383453369
Number of Workers: 3
Test: 4 Using: albumentations
Time: 2.2603540420532227
Number of Workers: 4
Test: 5 Using: albumentations
Time: 2.158949613571167
Number of Workers: 5
Test: 6 Using: albumentations
Time: 2.470766544342041
Number of Workers: 6
Test: 7 Using: albumentations
Time: 2.17976450920105
Number of Workers: 7
Test: 8 Using: albumentations
Time: 2.3888444900512695
Number of Workers: 8
Test: 9 Using: albumentations
Time: 2.1898529529571533
Number of Workers: 9
Test: 0 Using: skimage
Time: 19.045767068862915
Number of Workers: 0
Test: 1 Using: skimage
Time: 19.040592670440674
Number of Workers: 1
Test: 2 Using: skimage
Time: 11.070249080657959
Number of Workers: 2
Test: 3 Using: skimage
Time: 7.869706392288208
Number of Workers: 3
Test: 4 Using: skimage
Time: 6.358371257781982
Number of Workers: 4
Test: 5 Using: skimage
Time: 5.45630955696106
Number of Workers: 5
Test: 6 Using: skimage
Time: 4.961841821670532
Number of Workers: 6
Test: 7 Using: skimage
Time: 4.459730386734009
Number of Workers: 7
Test: 8 Using: skimage
Time: 3.968627452850342
Number of Workers: 8
Test: 9 Using: skimage
Time: 3.6736652851104736
Number of Workers: 9
from aucmedi.
Switched to albumentations as default resize
from aucmedi.
Related Issues (20)
- DataGenerator iterations HOT 1
- TF dataset from generator: unknown number of iterations in first epoch HOT 1
- TF dataset: Improve CPU performance HOT 3
- Benchmark: loading times keras.utils.sequence vs tf.datasets HOT 1
- Rollback to keras.Sequence again? HOT 1
- Reduce codecov coverage drop fail rate
- Training freeze at end of first epoch (validation computation) HOT 1
- Misplaced link in the tutorials HOT 1
- Wasserstein Distance add to loss function
- Codecov token issue HOT 1
- Add Mac M1 Apple Silicon Support HOT 1
- pathology slide interface with samplify? HOT 1
- AutoML indicates training for 10 Epochs but then trains for 500 when reaching 10 HOT 2
- Submodule dependency issue (classification-model-3D & Keras 3) HOT 2
- ModuleNotFoundError: No module named 'keras.engine' HOT 2
- Regression? HOT 2
- Add XAI SHAP
- Compatibility Issue with TensorFlow Addons and TensorFlow 2.14.0 HOT 3
- Compatibility Issues with tf.keras.metrics.F1Score on Python 3.9 and 3.10 HOT 1
- Dockerfile: change aucmedi install via setup.py to requirements.txt for more reproducibility
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 aucmedi.