Differentiable Neural Computers and family, for Pytorch

Includes:

1. Differentiable Neural Computers (DNC)
2. Sparse Access Memory (SAM)
3. Sparse Differentiable Neural Computers (SDNC)

This is an implementation of Differentiable Neural Computers, described in the paper Hybrid computing using a neural network with dynamic external memory, Graves et al. and Sparse DNCs (SDNCs) and Sparse Access Memory (SAM) described in Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes.

Install

pip install dnc

From source

git clone https://github.com/ixaxaar/pytorch-dnc
cd pytorch-dnc
pip install -r ./requirements.txt
pip install -e .

For using fully GPU based SDNCs or SAMs, install FAISS:

conda install faiss-gpu -c pytorch

pytest is required to run the test

Architecure

Usage

Constructor Parameters:

Following are the constructor parameters:

Following are the constructor parameters:

Following are the forward pass parameters:

Example usage

from dnc import DNC

rnn = DNC(
  input_size=64,
  hidden_size=128,
  rnn_type='lstm',
  num_layers=4,
  nr_cells=100,
  cell_size=32,
  read_heads=4,
  batch_first=True,
  gpu_id=0
)

(controller_hidden, memory, read_vectors) = (None, None, None)

output, (controller_hidden, memory, read_vectors) = \
  rnn(torch.randn(10, 4, 64), (controller_hidden, memory, read_vectors), reset_experience=True)

Debugging

The debug option causes the network to return its memory hidden vectors (numpy ndarrays) for the first batch each forward step. These vectors can be analyzed or visualized, using visdom for example.

from dnc import DNC

rnn = DNC(
  input_size=64,
  hidden_size=128,
  rnn_type='lstm',
  num_layers=4,
  nr_cells=100,
  cell_size=32,
  read_heads=4,
  batch_first=True,
  gpu_id=0,
  debug=True
)

(controller_hidden, memory, read_vectors) = (None, None, None)

output, (controller_hidden, memory, read_vectors), debug_memory = \
  rnn(torch.randn(10, 4, 64), (controller_hidden, memory, read_vectors), reset_experience=True)

Memory vectors returned by forward pass (np.ndarray):

Constructor Parameters:

Following are the constructor parameters:

Following are the forward pass parameters:

Example usage

from dnc import SDNC

rnn = SDNC(
  input_size=64,
  hidden_size=128,
  rnn_type='lstm',
  num_layers=4,
  nr_cells=100,
  cell_size=32,
  read_heads=4,
  sparse_reads=4,
  batch_first=True,
  gpu_id=0
)

(controller_hidden, memory, read_vectors) = (None, None, None)

output, (controller_hidden, memory, read_vectors) = \
  rnn(torch.randn(10, 4, 64), (controller_hidden, memory, read_vectors), reset_experience=True)

Debugging

The debug option causes the network to return its memory hidden vectors (numpy ndarrays) for the first batch each forward step. These vectors can be analyzed or visualized, using visdom for example.

from dnc import SDNC

rnn = SDNC(
  input_size=64,
  hidden_size=128,
  rnn_type='lstm',
  num_layers=4,
  nr_cells=100,
  cell_size=32,
  read_heads=4,
  batch_first=True,
  sparse_reads=4,
  temporal_reads=4,
  gpu_id=0,
  debug=True
)

(controller_hidden, memory, read_vectors) = (None, None, None)

output, (controller_hidden, memory, read_vectors), debug_memory = \
  rnn(torch.randn(10, 4, 64), (controller_hidden, memory, read_vectors), reset_experience=True)

Memory vectors returned by forward pass (np.ndarray):

Constructor Parameters:

Following are the constructor parameters:

Following are the forward pass parameters:

Example usage

from dnc import SAM

rnn = SAM(
  input_size=64,
  hidden_size=128,
  rnn_type='lstm',
  num_layers=4,
  nr_cells=100,
  cell_size=32,
  read_heads=4,
  sparse_reads=4,
  batch_first=True,
  gpu_id=0
)

(controller_hidden, memory, read_vectors) = (None, None, None)

output, (controller_hidden, memory, read_vectors) = \
  rnn(torch.randn(10, 4, 64), (controller_hidden, memory, read_vectors), reset_experience=True)

Debugging

The debug option causes the network to return its memory hidden vectors (numpy ndarrays) for the first batch each forward step. These vectors can be analyzed or visualized, using visdom for example.

from dnc import SAM

rnn = SAM(
  input_size=64,
  hidden_size=128,
  rnn_type='lstm',
  num_layers=4,
  nr_cells=100,
  cell_size=32,
  read_heads=4,
  batch_first=True,
  sparse_reads=4,
  gpu_id=0,
  debug=True
)

(controller_hidden, memory, read_vectors) = (None, None, None)

output, (controller_hidden, memory, read_vectors), debug_memory = \
  rnn(torch.randn(10, 4, 64), (controller_hidden, memory, read_vectors), reset_experience=True)

Memory vectors returned by forward pass (np.ndarray):

Tasks

Copy task (with curriculum and generalization)

The copy task, as descibed in the original paper, is included in the repo.

From the project root:

python ./tasks/copy_task.py -cuda 0 -optim rmsprop -batch_size 32 -mem_slot 64 # (like original implementation)

python ./tasks/copy_task.py -cuda 0 -lr 0.001 -rnn_type lstm -nlayer 1 -nhlayer 2 -dropout 0 -mem_slot 32 -batch_size 1000 -optim adam -sequence_max_length 8 # (faster convergence)

For SDNCs:
python ./tasks/copy_task.py -cuda 0 -lr 0.001 -rnn_type lstm -memory_type sdnc -nlayer 1 -nhlayer 2 -dropout 0 -mem_slot 100 -mem_size 10  -read_heads 1 -sparse_reads 10 -batch_size 20 -optim adam -sequence_max_length 10

and for curriculum learning for SDNCs:
python ./tasks/copy_task.py -cuda 0 -lr 0.001 -rnn_type lstm -memory_type sdnc -nlayer 1 -nhlayer 2 -dropout 0 -mem_slot 100 -mem_size 10  -read_heads 1 -sparse_reads 4 -temporal_reads 4 -batch_size 20 -optim adam -sequence_max_length 4 -curriculum_increment 2 -curriculum_freq 10000

For the full set of options, see:

python ./tasks/copy_task.py --help

The copy task can be used to debug memory using Visdom.

Additional step required:

pip install visdom
python -m visdom.server

Open http://localhost:8097/ on your browser, and execute the copy task:

python ./tasks/copy_task.py -cuda 0

The visdom dashboard shows memory as a heatmap for batch 0 every -summarize_freq iteration:

Generalizing Addition task

The adding task is as described in this github pull request. This task

• creates one-hot vectors of size input_size, each representing a number
• feeds a sentence of them to a network
• the output of which is added to get the sum of the decoded outputs

The task first trains the network for sentences of size ~100, and then tests if the network genetalizes for lengths ~1000.

python ./tasks/adding_task.py -cuda 0 -lr 0.0001 -rnn_type lstm -memory_type sam -nlayer 1 -nhlayer 1 -nhid 100 -dropout 0 -mem_slot 1000 -mem_size 32 -read_heads 1 -sparse_reads 4 -batch_size 20 -optim rmsprop -input_size 3 -sequence_max_length 100

Generalizing Argmax task

The second adding task is similar to the first one, except that the network's output at the last time step is expected to be the argmax of the input.

python ./tasks/argmax_task.py -cuda 0 -lr 0.0001 -rnn_type lstm -memory_type dnc -nlayer 1 -nhlayer 1 -nhid 100 -dropout 0 -mem_slot 100 -mem_size 10 -read_heads 2 -batch_size 1 -optim rmsprop -sequence_max_length 15 -input_size 10 -iterations 10000

Code Structure

1. DNCs:

• dnc/dnc.py - Controller code.
• dnc/memory.py - Memory module.

1. SDNCs:

1. SAMs:

• dnc/sam.py - Controller code, inherits dnc.py.
• dnc/sparse_memory.py - Memory module.
• dnc/flann_index.py - Memory index using kNN.

1. Tests:

• All tests are in ./tests folder.

General noteworthy stuff

FLANN can be installed either from pip (automatically as a dependency), or from source (e.g. for multithreading via OpenMP):

# install openmp first: e.g. `sudo pacman -S openmp` for Arch.
git clone git://github.com/mariusmuja/flann.git
cd flann
mkdir build
cd build
cmake ..
make -j 4
sudo make install

FAISS can be installed using:

conda install faiss-gpu -c pytorch

FAISS is much faster, has a GPU implementation and is interoperable with pytorch tensors. We try to use FAISS by default, in absence of which we fall back to FLANN.

1. nans in the gradients are common, try with different batch sizes

Repos referred to for creation of this repo: