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_0.02.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 4.000697612762451
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: 4.206968307495117
Linear Weight Rank: 178
Intra Cos: 0.35668548941612244
Inter Cos: 0.009473513811826706
Norm Quadratic Average: 2.716132879257202
Nearest Class Center Accuracy: 0.975625

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.077599287033081
Linear Weight Rank: 4
Intra Cos: 0.7138060331344604
Inter Cos: 0.02576672099530697
Norm Quadratic Average: 3.369877576828003
Nearest Class Center Accuracy: 0.982

Output Layer:
Intra Cos: 0.8231927156448364
Inter Cos: 0.023056253790855408
Norm Quadratic Average: 6.802839279174805
Nearest Class Center Accuracy: 0.983875

Test Set:
Average Loss: 0.1781398720741272
Accuracy: 0.9885
NC1 Within Class Collapse: 2.584664821624756
NC2 Equinorm: Features: 0.04226573556661606, Weights: 0.013943761587142944
NC2 Equiangle: Features: 0.43407432238260907, Weights: 0.4107784032821655
NC3 Self-Duality: 0.02112557739019394
NC4 NCC Mismatch: 0.020499999999999963

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 4.000697612762451
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: 4.206968307495117
Linear Weight Rank: 178
Intra Cos: 0.3520447015762329
Inter Cos: 0.012685209512710571
Norm Quadratic Average: 2.729619026184082
Nearest Class Center Accuracy: 0.97

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.077599287033081
Linear Weight Rank: 4
Intra Cos: 0.7070424556732178
Inter Cos: 0.03649410977959633
Norm Quadratic Average: 3.401029109954834
Nearest Class Center Accuracy: 0.979

Output Layer:
Intra Cos: 0.8145927786827087
Inter Cos: 0.03494652733206749
Norm Quadratic Average: 6.852935791015625
Nearest Class Center Accuracy: 0.9825

