================================================================================
Model Configuration (CRITICAL FOR INFERENCE)
================================================================================
modelCategory: SOTA
Task: classification
Genome: [[[8, 1], [2, 1]], [[9, 1], [1, 0]], [[4, 2], [5, 3]], [[1, 1], [8, 3]], [[4, 5], [4, 5]]]
Architecture: AdapterGenotype(ops=[('channel_attention', 1), ('conv_1x1', 1), ('spatial_attention', 1), ('skip_connect', 0), ('sep_conv_5x5', 2), ('dil_conv_3x3', 3), ('skip_connect', 1), ('channel_attention', 3), ('sep_conv_5x5', 5), ('sep_conv_5x5', 5)], ops_concat=[4, 6])
backbone: yolov8n
search_space: micro
num_cells: 3
num_classes: 10
image_size: 224
class_names: ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
================================================================================
Performance Metrics
================================================================================
Params: 3.26208 MB
Forward FLOPs: 293.245254 M
Training FLOPs: 704.150110 M [thop]
Training Efficiency: 20.0% savings
--------------------------------------------------------------------------------
Epoch  | Train Acc  | Valid Acc  | Error      | FLOPs     
--------------------------------------------------------------------------------
0      | 54.29      | 73.15      | 26.85      | 704.15    
