Spikey/config.yaml

name: EXAMPLE

latent_projector:
  type: 'fc'  # Type of latent projector: 'fc', 'rnn', 'fourier'
  input_size: 1953  # Input size for the Latent Projector (length of snippets).
  latent_size: 4  # Size of the latent representation before message passing.
  layer_shapes: [32, 8]  # List of layer sizes for the latent projector if type is 'fc' or 'fourier'.
  activations: ['ReLU', 'ReLU']  # Activation functions for the latent projector layers if type is 'fc' or 'fourier'.
  rnn_hidden_size: 4  # Hidden size for the RNN projector if type is 'rnn'.
  rnn_num_layers: 1  # Number of layers for the RNN projector if type is 'rnn'.
  num_frequencies: 16  # Number of frequency bins for the Fourier decomposition if type is 'fourier'.
  pass_raw_len: 50  # Number of last samples to pass raw to the net in addition to frequencies (null = all) if type is 'fourier'.

middle_out:
  region_latent_size: 4  # Size of the latent representation after message passing.
  residual: false # Wether to use a ResNet style setup. Requires region_latent_size = latent_size
  num_peers: 3  # Number of closest peers to consider.

predictor:
  layer_shapes: [3]  # List of layer sizes for the predictor.
  activations: ['ReLU']  # Activation functions for the predictor layers.

training:
  epochs: 1024  # Number of training epochs.
  batch_size: 32  # Batch size for training.
  num_batches: 1  # Number of batches per epoch.
  learning_rate: 0.01  # Learning rate for the optimizer.
  peer_gradients: true # Wether we allow gradients flow to the latent projector for peers. Leads to higher sample efficiency but also less stability.
  eval_freq: -1  # Frequency of evaluation during training (in epochs).
  save_path: models  # Directory to save the best model and encoder.

evaluation:
  full_compression: false  # Perform full compression during evaluation.

bitstream_encoding:
  type: identity  # Bitstream encoding type: 'arithmetic', 'identity', 'bzip2'.

data:
  url: https://content.neuralink.com/compression-challenge/data.zip  # URL to download the dataset.
  directory: data  # Directory to extract and store the dataset.
  split_ratio: 0.8  # Ratio to split the data into train and test sets.
  cut_length: null  # Optional length to cut sequences to.

profiler:
  enable: false  # Enable profiler.

---

name: DEFAULT
project: Spikey_1

slurm:
  name: 'Spikey_{config[name]}'
  partitions:
    - single
  standard_output: ./reports/slurm/out_%A_%a.log
  standard_error: ./reports/slurm/err_%A_%a.log
  num_parallel_jobs: 50
  cpus_per_task: 8
  memory_per_cpu: 4000
  time_limit: 1440  # in minutes
  ntasks: 1
  venv: '.venv/bin/activate'
  sh_lines:
    - 'mkdir -p {tmp}/wandb'
    - 'mkdir -p {tmp}/local_pycache'
    - 'export PYTHONPYCACHEPREFIX={tmp}/local_pycache'

runner: spikey

scheduler:
  reps_per_version: 1
  agents_per_job: 100
  reps_per_agent: 1

wandb:
  project: '{config[project]}'
  group: '{config[name]}'
  job_type: '{delta_desc}'
  name: '{job_id}_{task_id}:{run_id}:{rand}={config[name]}_{delta_desc}'
  #tags:
  #  - '{config[env][name]}'
  #  - '{config[algo][name]}'
  sync_tensorboard: False
  monitor_gym: False
  save_code: False

evaluation:
  full_compression: false

bitstream_encoding:
  type: identity

data:
  url: https://content.neuralink.com/compression-challenge/data.zip
  directory: data
  split_ratio: 0.8
  cut_length: null

profiler:
  enable: false

training:
  eval_freq: -1 # 8
  save_path: models
  peer_gradients: True

middle_out:
  residual: False
---
name: FC
import: $

latent_projector:
  type: fc
  input_size: 1953
  latent_size: 4
  layer_shapes: [32, 8]
  activations: ['ReLU', 'ReLU']

middle_out:
  region_latent_size: 4
  num_peers: 3

predictor:
  layer_shapes: [3]
  activations: ['ReLU']

training:
  epochs: 1024
  batch_size: 32
  num_batches: 1
  learning_rate: 0.01
---
name: FC6
import: $

latent_projector:
  type: fc
  input_size: 195
  latent_size: 4
  layer_shapes: [16]
  activations: ['ReLU']

middle_out:
  region_latent_size: 8
  num_peers: 3

predictor:
  layer_shapes: [3]
  activations: ['ReLU']

training:
  epochs: 1024
  batch_size: 16
  num_batches: 1
  learning_rate: 0.01
---
name: RNN
import: $

latent_projector:
  type: rnn
  input_size: 1953
  latent_size: 4
  rnn_hidden_size: 3
  rnn_num_layers: 2

middle_out:
  region_latent_size: 4
  num_peers: 3

predictor:
  layer_shapes: [3]
  activations: ['ReLU']

training:
  epochs: 1024
  batch_size: 64
  num_batches: 2
  learning_rate: 0.01