Home

Awesome

Deep Learning Model Zoo

This repository contains implementations of various deep learning algorithms in Theano/Lasagne.

Running a model

To run a model, you may use the run.py launch script.

python run.py train \
  --dataset <dataset> \
  --model <epochs> \
  --alg <opt_alg> \
  --n_batch <batch_size> \
  --lr <learning_rate> \
  -e <num_epochs> \
  -l <log_name>

Alternatively, you may use the Makefile included in the root dir; typing make train will start training. There are also several additional parameters that can be configured inside the Makefile.

The model will periodically save its weights and report training/validation losses in the logfile.

Algorithms

The following algorithms are available.

Supervised learning models

Semi-supervised models

Unsupervised models

Datasets

The following datasets are currently available:

Optimization methods

Currently, we may train the models using:

Feedback

Send feedback to Volodymyr Kuleshov. Some models contain snippets from other users' repositories; let me know if I forgot to cite anyone.