- Requirements
- numpy, pytorch
- For overview of code + some plots, check out
main.ipynb
- Generate Ising model data:
- run
python generate_data.py
- Place correlated .npy file in correct temperature directory
- run
- Create uncorrelated samples in
supervised_convnet/generate_uncorrelated_data.py
- Set
data
variable to be path of the Ising model data (of each temperature) - Place uncorrelated .npy file in correct temperature directory
- Set
- Train neural network to distinguish between correlated/uncorrelated samples in temperature directory e.g.
supervised_convnet/t_1/train.py
- Make sure both correlated and uncorrelated .npy file in
supervised_convnet/t_1
- Make sure both correlated and uncorrelated .npy file in
- Neural network architecture in
supervised_convnet/supervised_convnet.py
- Also contains
IsingDataset
class for pytorch data set loading
- Also contains
renormalization's Introduction
renormalization's People
renormalization's Issues
Mon Feb 26 exps
coarse grain the network
- retry with tanh and relu and see if i get zero train loss
do shuffling svd exps & pca regression:
MNIST: Classification with nonlinearity
MNIST: Classification with nonlinearity
Try experiment with L2 set to what we have now and an experiment without L2
Start with easy nonlinearities like tanh and then try ReLU
for k in {1..14}; do python -u mnist_classification.py ./data --coarsegrain_blocksize $k --num_hidden_features $i --num_train_samples $j --fileprefix tanhlr0.1_mnistAUG05 --nonlinearity tanh --train_method gradient_descent --epochs 150 --lr 0.1 ; done
for k in {1..14}; do python -u mnist_classification.py ./data --coarsegrain_blocksize $k --num_hidden_features $i --num_train_samples $j --fileprefix tanhlr0.1_wd0_mnistAUG06 --nonlinearity tanh --train_method gradient_descent --epochs 150 --lr 0.1 --wd 0.0000000000000000000000001; done
CIFAR: classification with nonlinearity
for k in 1 2 3 4 5 6 7 8 9 11 17; do python -u cifar_classification_randomfeatures.py ./data --coarsegrain_blocksize $k --num_hidden_features $i --num_train_samples $j --fileprefix linelr0.001_wd1em5_cifarAUG15 --nonlinearity line --train_method gradient_descent --epochs 150 --lr 0.001; done # --wd 0.0000000000000000000000001
for k in 1 2 3 4 5 6 7 8 9 11 17; do python -u cifar_classification_randomfeatures.py ./data --coarsegrain_blocksize $k --num_hidden_features $i --num_train_samples $j --fileprefix tanhlr0.1_wd1em5_cifarAUG15 --nonlinearity tanh --train_method gradient_descent --epochs 150 --lr 0.1; done # --wd 0.0000000000000000000000001
Whole network
for k in 1 2 3 4 5 6 7 8 9 11 17; do python -u cifar_classification_randomfeatures_wholenetwork.py ./data --coarsegrain_blocksize $k --num_hidden_features $i --num_train_samples $j --fileprefix linelr0.1_wd1em5_cifar_fullnetAUG16 --nonlinearity line--train_method gradient_descent --epochs 150 --lr 0.1; done # --wd 0.0000000000000000000000001
for k in 1 2 3 4 5 6 7 8 9 11 17; do python -u cifar_classification_randomfeatures_wholenetwork.py ./data --coarsegrain_blocksize $k --num_hidden_features $i --num_train_samples $j --fileprefix tanhlr0.1_wd1em5_cifar_fullnetAUG16 --nonlinearity tanh --train_method gradient_descent --epochs 150 --lr 0.1; done # --wd 0.0000000000000000000000001
for k in 1 2 3 4 5 6 7 8 9 11 17; do python -u cifar_classification_randomfeatures_wholenetwork.py ./data --coarsegrain_blocksize $k --num_hidden_features $i --num_train_samples $j --fileprefix relulr0.001_wd1em5_cifar_fullnetAUG16 --nonlinearity relu --train_method gradient_descent --epochs 150 --lr 0.001; done # --wd 0.0000000000000000000000001
SVD shuffling exp.
fractional coarse-graining
for k in 28 27 25 23 21 19 17 15 13 11 9 7 5 3 1; do python -u mnist_classification_wholenetwork.py ./data --target_size $k --num_hidden_features $j --num_train_samples 60000 --fileprefix relulr0.1_mnist_fullnet_fractional_cg_DEC04 --lr 0.1 --nonlinearity relu --epochs 150 --upsample; done # --wd 0.0000000000000000000000001
for k in 28 27 25 23 21 19 17 15 13 11 9 7 5 3 1; do python -u mnist_classification_wholenetwork.py ./data --target_size $k --num_hidden_features $j --num_train_samples 60000 --fileprefix linelr0.1_mnist_fullnet_fractional_cg_DEC04 --lr 0.1 --nonlinearity relu --epochs 150 --upsample; done # --wd 0.0000000000000000000000001
Try non-averaging kernels instead of just straight averaging
check accuracy function mnist
reduce learning rate for linear regression exp. + lambda
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.