Some tuning and updated README
This commit is contained in:
parent
cd62505ef1
commit
7062569df1
@ -44,8 +44,7 @@ Based on an expected distribution of deltas that have to be transmitted, an effi
|
||||
|
||||
- All currently implemented bitstream encoders are rather naive. We know that lead values from the N1 only have 10-bit precision, but the WAV file provides us with 32-bit floats. All my bitstream encoders are also based on 32-bit floats; discretizing back into the 10-bit space would be a low-hanging fruit for ~3.2x compression.
|
||||
- Since we merely encode the remaining delta, we can go even more efficient by constructing something along the lines of a Huffman tree.
|
||||
- Loss is not coming down during training... So basically nothing works right now. But the text I wrote is cool, right?
|
||||
- Make a logo
|
||||
- All trained models stick mostly suck. Im not beating a compression ratio of ~2x (not counting bitstream encoder)
|
||||
|
||||
## Installation
|
||||
|
||||
|
||||
183
config.yaml
183
config.yaml
@ -2,13 +2,12 @@ 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).
|
||||
input_size: 1953 # Input size for the Latent Projector (length of snippets). (=0.1s)
|
||||
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:
|
||||
@ -25,7 +24,8 @@ training:
|
||||
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.
|
||||
peer_gradients_factor: 0.33 # Factor for gradients acting on predictor throught peers. 0.0 = detach gradients.
|
||||
value_scale: 1 # Normalize data by dividing values by this (and multiple outputs)
|
||||
eval_freq: -1 # Frequency of evaluation during training (in epochs).
|
||||
save_path: models # Directory to save the best model and encoder.
|
||||
|
||||
@ -47,7 +47,7 @@ profiler:
|
||||
---
|
||||
|
||||
name: DEFAULT
|
||||
project: Spikey_1
|
||||
project: Spikey_2
|
||||
|
||||
slurm:
|
||||
name: 'Spikey_{config[name]}'
|
||||
@ -70,7 +70,7 @@ runner: spikey
|
||||
|
||||
scheduler:
|
||||
reps_per_version: 1
|
||||
agents_per_job: 100
|
||||
agents_per_job: 8
|
||||
reps_per_agent: 1
|
||||
|
||||
wandb:
|
||||
@ -81,9 +81,9 @@ wandb:
|
||||
#tags:
|
||||
# - '{config[env][name]}'
|
||||
# - '{config[algo][name]}'
|
||||
sync_tensorboard: False
|
||||
monitor_gym: False
|
||||
save_code: False
|
||||
sync_tensorboard: false
|
||||
monitor_gym: false
|
||||
save_code: false
|
||||
|
||||
evaluation:
|
||||
full_compression: false
|
||||
@ -103,10 +103,11 @@ profiler:
|
||||
training:
|
||||
eval_freq: -1 # 8
|
||||
save_path: models
|
||||
peer_gradients: True
|
||||
peer_gradients_factor: 0.25
|
||||
value_scale: 1000
|
||||
|
||||
middle_out:
|
||||
residual: False
|
||||
residual: false
|
||||
---
|
||||
name: FC
|
||||
import: $
|
||||
@ -121,6 +122,7 @@ latent_projector:
|
||||
middle_out:
|
||||
region_latent_size: 4
|
||||
num_peers: 3
|
||||
residual: true
|
||||
|
||||
predictor:
|
||||
layer_shapes: [3]
|
||||
@ -132,19 +134,20 @@ training:
|
||||
num_batches: 1
|
||||
learning_rate: 0.01
|
||||
---
|
||||
name: FC6
|
||||
name: FC_AblLR
|
||||
import: $
|
||||
|
||||
latent_projector:
|
||||
type: fc
|
||||
input_size: 195
|
||||
input_size: 1953
|
||||
latent_size: 4
|
||||
layer_shapes: [16]
|
||||
activations: ['ReLU']
|
||||
layer_shapes: [32, 8]
|
||||
activations: ['ReLU', 'ReLU']
|
||||
|
||||
middle_out:
|
||||
region_latent_size: 8
|
||||
region_latent_size: 4
|
||||
num_peers: 3
|
||||
residual: true
|
||||
|
||||
predictor:
|
||||
layer_shapes: [3]
|
||||
@ -152,9 +155,13 @@ predictor:
|
||||
|
||||
training:
|
||||
epochs: 1024
|
||||
batch_size: 16
|
||||
batch_size: 32
|
||||
num_batches: 1
|
||||
learning_rate: 0.01
|
||||
device: cpu
|
||||
|
||||
grid:
|
||||
training.learning_rate: [0.1, 0.01, 0.001, 0.0001]
|
||||
---
|
||||
name: RNN
|
||||
import: $
|
||||
@ -169,6 +176,7 @@ latent_projector:
|
||||
middle_out:
|
||||
region_latent_size: 4
|
||||
num_peers: 3
|
||||
residual: true
|
||||
|
||||
predictor:
|
||||
layer_shapes: [3]
|
||||
@ -176,6 +184,147 @@ predictor:
|
||||
|
||||
training:
|
||||
epochs: 1024
|
||||
batch_size: 64
|
||||
batch_size: 32
|
||||
num_batches: 2
|
||||
learning_rate: 0.01
|
||||
---
|
||||
name: FOURIER
|
||||
import: $
|
||||
|
||||
latent_projector:
|
||||
type: fourier
|
||||
input_size: 19531 # 1s
|
||||
latent_size: 8
|
||||
layer_shapes: [32, 8]
|
||||
activations: ['ReLU', 'ReLU']
|
||||
pass_raw_len: 1953 # 0.1s
|
||||
|
||||
middle_out:
|
||||
region_latent_size: 8
|
||||
num_peers: 3
|
||||
residual: true
|
||||
|
||||
predictor:
|
||||
layer_shapes: [3]
|
||||
activations: ['ReLU']
|
||||
|
||||
training:
|
||||
epochs: 1024
|
||||
batch_size: 32
|
||||
num_batches: 16
|
||||
learning_rate: 0.01
|
||||
---
|
||||
name: FC_AblPeerGrad # Best: 0.33
|
||||
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: 2
|
||||
residual: true
|
||||
|
||||
predictor:
|
||||
layer_shapes: [3]
|
||||
activations: ['ReLU']
|
||||
|
||||
training:
|
||||
epochs: 1024
|
||||
batch_size: 16
|
||||
num_batches: 1
|
||||
learning_rate: 0.01
|
||||
device: cpu
|
||||
|
||||
grid:
|
||||
training:
|
||||
peer_gradients_factor: [0.0, 0.1, 0.25, 0.33, 0.5, 1.0]
|
||||
---
|
||||
name: FC_NoPeer # Worse
|
||||
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: 0
|
||||
residual: true
|
||||
|
||||
predictor:
|
||||
layer_shapes: [3]
|
||||
activations: ['ReLU']
|
||||
|
||||
training:
|
||||
epochs: 1024
|
||||
batch_size: 16
|
||||
num_batches: 1
|
||||
learning_rate: 0.01
|
||||
device: cpu
|
||||
|
||||
---
|
||||
name: FC_ScaleAbl # Best: 1000
|
||||
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
|
||||
residual: true
|
||||
|
||||
predictor:
|
||||
layer_shapes: [3]
|
||||
activations: ['ReLU']
|
||||
|
||||
training:
|
||||
epochs: 1024
|
||||
batch_size: 32
|
||||
num_batches: 1
|
||||
learning_rate: 0.01
|
||||
device: cpu
|
||||
|
||||
grid:
|
||||
training.value_scale: [1, 100, 1000, 10000]
|
||||
---
|
||||
name: FC_BSAbl2
|
||||
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
|
||||
residual: true
|
||||
|
||||
predictor:
|
||||
layer_shapes: [3]
|
||||
activations: ['ReLU']
|
||||
|
||||
training:
|
||||
epochs: 1024
|
||||
batch_size: 32
|
||||
num_batches: 1
|
||||
learning_rate: 0.01
|
||||
device: cpu
|
||||
|
||||
grid:
|
||||
training.batch_size: [64, 128, 256]
|
||||
Loading…
Reference in New Issue
Block a user