Comments (4)
The 120 classes not unique.
idx120 = list(set(idx120))
len(idx120)
Out[4]: 110
from fast-autoaugment.
-
Sorry for the mistake. We modified the code by mistake for another issue.
First, we sample 500000 training data(approximately 500 samples for each 1k classes) and then we sample 120 classes. This will get us approximately 500 samples for each random 120 classes. -
As you pointed out, we used 110 classes by mistake. This is not intended. The result in our paper was from this 110 classes. If you want to, please make a pull request which modify code to use exclusive 120 classes. It might lead to a slightly better result.
Thanks for reporting this!
from fast-autoaugment.
Thanks for the reply! BTW, it is a great work.
- I swap the sequence of the operations by first get the samples from 120 classes and then get the 6000 splits.
- An easy way to get 120 unique classes can be:
idx120 = sorted(random.sample(list(range(1000)), k=120))
from fast-autoaugment.
@zhanghang1989 Thanks for the tip. I updated the repo as you suggested. But for the better reproducibility, I hardcoded indice. (Also swapping the sequence of code would be better, but I didn't do this at this time)
If you don't need any assistance on this matter, please close this issue.
from fast-autoaugment.
Related Issues (20)
- Inaccurate "accuracy" when testing uploaded model.
- Search policy on my custom dataset HOT 1
- IMAGENET url not found
- Can't run search.py HOT 3
- ValueError in search.py HOT 1
- Stuck after iteration HOT 1
- Can fast auto-augmentation be used for segmentation task?
- A question regarding the `RandomCrop`
- how to run the search.py, why search.py load ckpt before training? HOT 3
- Problems running search.py
- Pyramidnet Issue HOT 2
- Stuck in search.py HOT 5
- Stuck in search.py HOT 1
- TypeError: Error instantiating 'autoalbument.faster_autoaugment.models.policy_operations.ShiftRGB' : __init__() missing 1 required positional argument: 'temperature' HOT 1
- how to solve ββcannot import name 'PyStopwatch'β
- No module named 'watch' HOT 2
- Can I run search.py without redis address?
- WARNING: Did not find branch or tag '08f7d5e', assuming revision or ref.
- WARNING: Did not find branch or tag '08f7d5e', assuming revision or ref
- How to obtain the results of image enhancement
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fast-autoaugment.