Comments (5)
I didn't do any training tricks, aside from standard procedures like learning rate scheduling that are described in the paper. The code I originally used to get those numbers is almost identical to what is in the repo here. The only change is that I made things a bit neater for the release, but all of the actual processes are the same.
from cutout.
Thank you for your reply! I have tried to run many times, but still fail to achieve this accuracy. I think it is may because of the Pytorch version or hardware environment? I use Pytorch 1.4.0 and my environment is two titan x GPUs
Here is the record of my training process (.csv file) :
from cutout.
Thanks for uploading your log!
There's something weird going on here. I plotted the results from your log and one of my logs (with data augmentation, no cutout), and there are a couple differences. The most obvious one is that yours doesn't have the sudden jumps which the learning rate scheduling causes. It looks like in PyTorch 1.4.0 they deprecated the old scheduler, so maybe that's causing the issue. You can try replacing scheduler.step(epoch)
with scheduler.step()
in train.py. The other noticeable difference is that your model appears to be learning much slower than mine, but I have no idea what might be causing that issue. Your model starts out fast but then slows down a lot, so maybe it's also related to the scheduler. I would try changing that and see how it does.
from cutout.
Thanks for your advice! I manage to achieve the accuracy of 78%. I follow your advice by replacing scheduler.step(epoch) with scheduler.step(), and it works!
And here is my log:
cifar100_resnet18.zip
from cutout.
Thanks for the update! I've added some comments to the code in case anyone else runs into the same issue.
from cutout.
Related Issues (19)
- Was additional data augmented during testing? Such as Flip? HOT 1
- Why does resnet18 in the report achieve such high accuracy? HOT 1
- Questions about the parameters of cutout in object detection? HOT 1
- Extending Cutout with a probability of when it is applied HOT 3
- Which version of SVHN is used to train? HOT 1
- problem in getting same output size as batch size from forward function
- Bug report same images are multiply generated when using multiple workers.
- Is other torch version suitable for this code? I can't install torch==0.4.0
- CutOut in Albumentations HOT 5
- Is there any change in Wide ResNet for STL10? HOT 8
- About Adam and AdaBelief
- I really like your idea, I think this is a very useful idea.
- What is the cutout region for Imagenet HOT 1
- Could you add a LICENSE.md? HOT 2
- Need Help Getting Cutout to work Properly HOT 2
- hi,I have a question about your paper?Could you give me some tips? HOT 2
- TypeError: 'tuple' object is not callable HOT 4
- nb_layers should be int 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 cutout.