Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_conic_epochs_200_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_314159_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.771787643432617
Linear Weight Rank: 16
Intra Cos: 0.07988917827606201
Inter Cos: 0.0017584841698408127
Norm Quadratic Average: 4.001680374145508
Nearest Class Center Accuracy: 0.948875

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.928809642791748
Linear Weight Rank: 178
Intra Cos: 0.2441999912261963
Inter Cos: 0.010438628494739532
Norm Quadratic Average: 3.735532283782959
Nearest Class Center Accuracy: 0.96975

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4366331100463867
Linear Weight Rank: 4
Intra Cos: 0.6789693832397461
Inter Cos: 0.029954001307487488
Norm Quadratic Average: 4.450931072235107
Nearest Class Center Accuracy: 0.9795

Output Layer:
Intra Cos: 0.8115128874778748
Inter Cos: 0.03273196518421173
Norm Quadratic Average: 9.850323677062988
Nearest Class Center Accuracy: 0.980625

Test Set:
Average Loss: 0.12907812786102296
Accuracy: 0.979
NC1 Within Class Collapse: 2.7122206687927246
NC2 Equinorm: Features: 0.042552754282951355, Weights: 0.01374216191470623
NC2 Equiangle: Features: 0.4333988030751546, Weights: 0.4008440574010213
NC3 Self-Duality: 0.03681856021285057
NC4 NCC Mismatch: 0.023499999999999965

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.771787643432617
Linear Weight Rank: 16
Intra Cos: 0.08033028990030289
Inter Cos: 0.003312898799777031
Norm Quadratic Average: 3.988335609436035
Nearest Class Center Accuracy: 0.9165

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.928809642791748
Linear Weight Rank: 178
Intra Cos: 0.24053329229354858
Inter Cos: 0.008697733283042908
Norm Quadratic Average: 3.7466533184051514
Nearest Class Center Accuracy: 0.961

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4366331100463867
Linear Weight Rank: 4
Intra Cos: 0.6718847155570984
Inter Cos: 0.031061062589287758
Norm Quadratic Average: 4.494315147399902
Nearest Class Center Accuracy: 0.9765

Output Layer:
Intra Cos: 0.8001694083213806
Inter Cos: 0.030198706313967705
Norm Quadratic Average: 9.930291175842285
Nearest Class Center Accuracy: 0.9775

