dodox/Spikey
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Better config for Feature Extractor

Browse Source
This commit is contained in:
Dominik Moritz Roth 2024-05-27 17:07:00 +02:00
parent 17ff693ee5
commit 8bf85d1a65
2 changed files with 39 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

70
config.yaml
View File

@ -1,41 +1,42 @@
name: EXAMPLE
feature_extractor:
- type: 'identity' # Pass the last n samples of the input data directly.
length: 8 # Number of last samples to pass directly. Use full input size if set to null.
- type: 'fourier' # Apply Fourier transform to the input data.
length: null # Use full input size if set to null. Fourier transform outputs both real and imaginary parts, doubling the size. (Computationally expensive)
- type: 'wavelet' # Apply selected wavelet transform to the input data.
wavelet_type: 'haar' # Haar wavelet is simple and fast, but may not capture detailed features well.
length: null # Use full input size if set to null.
- type: 'wavelet'
wavelet_type: 'cgau1' # Complex Gaussian wavelets are used for complex-valued signal analysis and capturing phase information.
length: null # Use full input size if set to null.
- type: 'wavelet'
wavelet_type: 'db1' # Daubechies wavelets provide a balance between time and frequency localization.
length: null # Use full input size if set to null. (Computationally expensive)
- type: 'wavelet'
wavelet_type: 'sym2' # Symlet wavelets are nearly symmetrical, offering improved phase characteristics over Daubechies.
length: null # Use full input size if set to null. (Computationally expensive)
- type: 'wavelet'
wavelet_type: 'coif1' # Coiflet wavelets have more vanishing moments, suitable for capturing polynomial trends.
length: null # Use full input size if set to null. (Computationally expensive)
- type: 'wavelet'
wavelet_type: 'bior1.3' # Biorthogonal wavelets provide perfect reconstruction and linear phase characteristics.
length: null # Use full input size if set to null. (Computationally expensive)
- type: 'wavelet'
wavelet_type: 'rbio1.3' # Reverse Biorthogonal wavelets are similar to Biorthogonal but optimized for different applications.
length: null # Use full input size if set to null. (Computationally expensive)
- type: 'wavelet'
wavelet_type: 'dmey' # Discrete Meyer wavelets offer good frequency localization, ideal for signals with oscillatory components.
length: null # Use full input size if set to null. (Computationally expensive)
- type: 'wavelet'
wavelet_type: 'morl' # Morlet wavelets are useful for time-frequency analysis due to their Gaussian-modulated sinusoid shape.
length: null # Use full input size if set to null. (Computationally expensive)
input_size: 1953 # Input size for the Feature Extractor (length of snippets). (=0.1s)
transforms:
- type: 'identity' # Pass the last n samples of the input data directly.
length: 8 # Number of last samples to pass directly. Use full input size if set to null.
- type: 'fourier' # Apply Fourier transform to the input data.
length: null # Use full input size if set to null. Fourier transform outputs both real and imaginary parts, doubling the size. (Computationally expensive)
- type: 'wavelet' # Apply selected wavelet transform to the input data.
wavelet_type: 'haar' # Haar wavelet is simple and fast, but may not capture detailed features well.
length: null # Use full input size if set to null.
- type: 'wavelet'
wavelet_type: 'cgau1' # Complex Gaussian wavelets are used for complex-valued signal analysis and capturing phase information.
length: null # Use full input size if set to null.
- type: 'wavelet'
wavelet_type: 'db1' # Daubechies wavelets provide a balance between time and frequency localization.
length: null # Use full input size if set to null. (Computationally expensive)
- type: 'wavelet'
wavelet_type: 'sym2' # Symlet wavelets are nearly symmetrical, offering improved phase characteristics over Daubechies.
length: null # Use full input size if set to null. (Computationally expensive)
- type: 'wavelet'
wavelet_type: 'coif1' # Coiflet wavelets have more vanishing moments, suitable for capturing polynomial trends.
length: null # Use full input size if set to null. (Computationally expensive)
- type: 'wavelet'
wavelet_type: 'bior1.3' # Biorthogonal wavelets provide perfect reconstruction and linear phase characteristics.
length: null # Use full input size if set to null. (Computationally expensive)
- type: 'wavelet'
wavelet_type: 'rbio1.3' # Reverse Biorthogonal wavelets are similar to Biorthogonal but optimized for different applications.
length: null # Use full input size if set to null. (Computationally expensive)
- type: 'wavelet'
wavelet_type: 'dmey' # Discrete Meyer wavelets offer good frequency localization, ideal for signals with oscillatory components.
length: null # Use full input size if set to null. (Computationally expensive)
- type: 'wavelet'
wavelet_type: 'morl' # Morlet wavelets are useful for time-frequency analysis due to their Gaussian-modulated sinusoid shape.
length: null # Use full input size if set to null. (Computationally expensive)
latent_projector:
type: 'fc' # Type of latent projector: 'fc', 'rnn', 'fourier'
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'.
@ -146,6 +147,11 @@ middle_out:
name: FC
import: $
feature_extractor:
input size: 10
transforms:
- type: 'identity'
latent_projector:
type: fc
input_size: 1953

2
models.py
View File

@ -24,7 +24,7 @@ class FeatureExtractor(nn.Module):
transforms = []
for item in config:
transform_type = item['type']
length = item.get('length', self.input_size)
length = item.get('length', None)
if length in [None, -1]:
length = self.input_size