Comments (7)
OK that works -- I can verify that running train_search.py
and training the resulting genotype gives comparable results to the DARTS
model in cnn/genotypes.py
.
from darts.
Yes, just copy & paste it into genotypes.py
as you described : )
Then, run python train.py --arch $NAME_OF_THE_ARCH --auxiliary --cutout
for evaluation.
from darts.
Cool thanks -- and how would you recommend sampling a random architecture? Something like this?
model = Network(args.init_channels, CIFAR_CLASSES, args.layers, criterion)
model.alphas_normal = Variable(torch.randn(k, num_ops))
model.alphas_reduce = Variable(torch.randn(k, num_ops))
random_genotype = model.genotype()
from darts.
Yep, that should do.
from darts.
I am also getting around 89% validation accuracy when running train_search.py
. Are these expected results for this step. I see no expected results for this in the documentation or paper.
from darts.
It looks fine. The validation acc during arch search does not tell too much because the weights are under-trained. You'll need to train the architecture from scratch in order to evaluate it and achieve ~2.83%.
from darts.
@quark0 hi, I'm wondering how many epochs do you train the searched architecture, I used the searched arch on epoch 49, and it it only gets 95.0 valid acc after retrained for 350 epochs
from darts.
Related Issues (20)
- Approximate Architecture Gradient
- Imagenet mobile setting
- Can not reproduce the search result on PTB dataset (Fig3)? HOT 5
- The discrepancy between DARTS and ENAS for RNN cell searching
- Indentation bugs HOT 1
- Why are stem.0.weight different in pretrained and searched CIFAR-10 architectures?
- Questions about DARTS
- Can you tell me how to calculate Search Cost? HOT 1
- When running train,py, why can't I get the same high accuracy as in train_search.py
- Training time on colab HOT 2
- About alpha HOT 1
- RuntimeError: cannot pin 'torch.cuda.DoubleTensor' on GPU on version 0.10.0
- About utils.accuracy
- Broken pipe issue HOT 1
- try to visulize the genotype but got error HOT 1
- Not much comments in code. HOT 2
- Implementation compatible with the recent PyTorch and CUDA version
- Can only achieve 93% accuracy on CIFAR10
- Please upadate codes for latest version of PyTorch
- confuse about the train_search/train/test
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 darts.