Comments (3)
from augmix.
Both Autocontrast and Histogram equalization (augmentations.equalize) can vary the distribution of contrast across images. Perhaps this provides some contrast robustness?
from augmix.
AutoContrast in PIL is a complicated histogram-based method that scales the image to take up the full range from min to max values, while the "contrast" corruption in ImageNet-C merely squishes inputs closer to their mean.
def contrast(x, severity=1):
c = [0.4, .3, .2, .1, .05][severity - 1]
x = np.array(x) / 255.
means = np.mean(x, axis=(0, 1), keepdims=True)
return np.clip((x - means) * c + means, 0, 1) * 255
from augmix.
Related Issues (20)
- Reproduce of Baseline
- A question in "third_party/WideResNet_pytorch/wideresnet.py out = self.relu2(self.bn2(self.conv1(out))) HOT 2
- `depth` is constant each `width` HOT 2
- There is a big gap between the results of the code and the results in the paper on CIFAR10-C HOT 2
- What about the performance on regular classification problems? HOT 5
- KL divergenve HOT 1
- Issue loading pretrained weights HOT 3
- mean and std for every channel is 0.5 instead of (0.5071, 0.4867. 0.4408) as mean and (0.2657, 0.2565, 0.2761) as std HOT 2
- Jensen–Shannon divergence HOT 2
- Corruption acc. of a Resnet50 trained on cifar10 with augmix HOT 2
- command for imagenet evaluation
- Use combined with Object Detection
- none
- Nan loss for ResNext backbone trained on cifar 100 HOT 1
- torch version 1.2.0 not compatible with GPU version HOT 1
- Little difference between with/without JSD loss HOT 1
- Can you share any acc information per epoch? HOT 3
- Testing with the best model HOT 4
- Repeated Evaluation in ImageNet 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 augmix.