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_338327_weight_decay_0.0005.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.799745559692383
Linear Weight Rank: 16
Intra Cos: 0.07988917827606201
Inter Cos: 0.0017584916204214096
Norm Quadratic Average: 4.001680850982666
Nearest Class Center Accuracy: 0.948875

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.873470306396484
Linear Weight Rank: 180
Intra Cos: 0.1778959184885025
Inter Cos: 0.0025877091102302074
Norm Quadratic Average: 5.445643901824951
Nearest Class Center Accuracy: 0.956875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.08076810836792
Linear Weight Rank: 4
Intra Cos: 0.6355417370796204
Inter Cos: 0.024250879883766174
Norm Quadratic Average: 6.854475975036621
Nearest Class Center Accuracy: 0.982125

Output Layer:
Intra Cos: 0.8165245056152344
Inter Cos: 0.03559834510087967
Norm Quadratic Average: 17.472923278808594
Nearest Class Center Accuracy: 0.9825

Test Set:
Average Loss: 0.08603798079490661
Accuracy: 0.983
NC1 Within Class Collapse: 2.786489963531494
NC2 Equinorm: Features: 0.04474962502717972, Weights: 0.017121447250247
NC2 Equiangle: Features: 0.4344319502512614, Weights: 0.3882254759470622
NC3 Self-Duality: 0.06015012785792351
NC4 NCC Mismatch: 0.030000000000000027

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.799745559692383
Linear Weight Rank: 16
Intra Cos: 0.0803302749991417
Inter Cos: 0.0033128950744867325
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: 8.873470306396484
Linear Weight Rank: 180
Intra Cos: 0.17525336146354675
Inter Cos: 0.007279899902641773
Norm Quadratic Average: 5.451490879058838
Nearest Class Center Accuracy: 0.9525

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.08076810836792
Linear Weight Rank: 4
Intra Cos: 0.6294514536857605
Inter Cos: 0.048172272741794586
Norm Quadratic Average: 6.925259113311768
Nearest Class Center Accuracy: 0.972

Output Layer:
Intra Cos: 0.8049127459526062
Inter Cos: 0.06455233693122864
Norm Quadratic Average: 17.648839950561523
Nearest Class Center Accuracy: 0.975

