Added an image classifciation task template for EfficientNetV2L embed…

david-thrower / cerebros-core-algorithm-alpha

The Cerebros package is an ultra-precise Neural Architecture Search (NAS) / AutoML that is intended to much more closely mimic biological neurons than conventional neural network architecture strategies.

Other

27 stars 4 forks source link

Added an image classifciation task template for EfficientNetV2L embed… #90

Closed david-thrower closed 1 year ago

david-thrower commented 1 year ago

Performance:

val-top-1-categorical-accuracy: 0.91657

Optima:

activation: relu predecessor_level_connection_affinity_factor_first: 1.19289 predecessor_level_connection_affinity_factor_main: 46.039 max_consecutive_lateral_connections: 11 p_lateral_connection: 24.7868 num_lateral_connection_tries_per_unit: 12 learning_rate: 2.30375e-5 epochs: 5 batch_size: 21 maximum_levels: 7 maximum_units_per_level: 10 maximum_neurons_per_unit: 5

cifar-mini-EffifientNetV2L

Aidyn-Lopez commented 1 year ago

I approve of these changes being merged.