Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_265358_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.191351890563965
Linear Weight Rank: 16
Intra Cos: 0.03299568220973015
Inter Cos: -0.006222444586455822
Norm Quadratic Average: 3.9938879013061523
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.145244598388672
Linear Weight Rank: 180
Intra Cos: 0.030030082911252975
Inter Cos: -0.004065678920596838
Norm Quadratic Average: 13.929381370544434
Nearest Class Center Accuracy: 0.59675

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7851314544677734
Linear Weight Rank: 4
Intra Cos: 0.04268466308712959
Inter Cos: -0.00965240877121687
Norm Quadratic Average: 14.320123672485352
Nearest Class Center Accuracy: 0.812875

Output Layer:
Intra Cos: 0.5650583505630493
Inter Cos: -0.13589531183242798
Norm Quadratic Average: 7.663926601409912
Nearest Class Center Accuracy: 0.981375

Test Set:
Average Loss: 0.6251850681304931
Accuracy: 0.769
NC1 Within Class Collapse: 5.2089691162109375
NC2 Equinorm: Features: 0.11290167272090912, Weights: 0.04100606217980385
NC2 Equiangle: Features: 0.11477914452552795, Weights: 0.03283095359802246
NC3 Self-Duality: 0.547744870185852
NC4 NCC Mismatch: 0.21799999999999997

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.191351890563965
Linear Weight Rank: 16
Intra Cos: 0.030431464314460754
Inter Cos: -0.004549724515527487
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: 8.145244598388672
Linear Weight Rank: 180
Intra Cos: 0.026852235198020935
Inter Cos: -0.004060016479343176
Norm Quadratic Average: 13.935972213745117
Nearest Class Center Accuracy: 0.599

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7851314544677734
Linear Weight Rank: 4
Intra Cos: 0.03252016752958298
Inter Cos: -0.005998136941343546
Norm Quadratic Average: 14.335989952087402
Nearest Class Center Accuracy: 0.715

Output Layer:
Intra Cos: 0.36633798480033875
Inter Cos: -0.06747200340032578
Norm Quadratic Average: 7.519873142242432
Nearest Class Center Accuracy: 0.7625

