Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_979323_weight_decay_0.05.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.8822895288467407
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222443655133247
Norm Quadratic Average: 3.9938876628875732
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 2.0261900424957275
Linear Weight Rank: 176
Intra Cos: 0.12152763456106186
Inter Cos: -0.012338925153017044
Norm Quadratic Average: 1.3399395942687988
Nearest Class Center Accuracy: 0.59475

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 1.9532403945922852
Linear Weight Rank: 4
Intra Cos: 0.183604896068573
Inter Cos: -0.000676187570206821
Norm Quadratic Average: 1.0883339643478394
Nearest Class Center Accuracy: 0.594

Output Layer:
Intra Cos: 0.1846301406621933
Inter Cos: 0.012886651791632175
Norm Quadratic Average: 1.2474991083145142
Nearest Class Center Accuracy: 0.583

Test Set:
Average Loss: 1.0126656112670898
Accuracy: 0.6075
NC1 Within Class Collapse: 8.544132232666016
NC2 Equinorm: Features: 0.1900731474161148, Weights: 0.04935465753078461
NC2 Equiangle: Features: 0.27468148867289227, Weights: 0.14376322428385416
NC3 Self-Duality: 0.0509076789021492
NC4 NCC Mismatch: 0.09250000000000003

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.8822895288467407
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.004549722652882338
Norm Quadratic Average: 3.9951601028442383
Nearest Class Center Accuracy: 0.583

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 2.0261900424957275
Linear Weight Rank: 176
Intra Cos: 0.11076745390892029
Inter Cos: 0.001296509988605976
Norm Quadratic Average: 1.3352988958358765
Nearest Class Center Accuracy: 0.5915

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 1.9532403945922852
Linear Weight Rank: 4
Intra Cos: 0.16438323259353638
Inter Cos: 0.0230637788772583
Norm Quadratic Average: 1.0827606916427612
Nearest Class Center Accuracy: 0.5915

Output Layer:
Intra Cos: 0.16905686259269714
Inter Cos: 0.03609275445342064
Norm Quadratic Average: 1.240181565284729
Nearest Class Center Accuracy: 0.583

