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_0.0005.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.113523483276367
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: 8.068493843078613
Linear Weight Rank: 180
Intra Cos: 0.029985113069415092
Inter Cos: -0.0040448815561831
Norm Quadratic Average: 13.796119689941406
Nearest Class Center Accuracy: 0.596875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7736661434173584
Linear Weight Rank: 4
Intra Cos: 0.042880456894636154
Inter Cos: -0.00963553786277771
Norm Quadratic Average: 14.189203262329102
Nearest Class Center Accuracy: 0.81625

Output Layer:
Intra Cos: 0.5659570097923279
Inter Cos: -0.1358427107334137
Norm Quadratic Average: 7.616620063781738
Nearest Class Center Accuracy: 0.98175

Test Set:
Average Loss: 0.6239989585876465
Accuracy: 0.7665
NC1 Within Class Collapse: 5.176041603088379
NC2 Equinorm: Features: 0.11406329274177551, Weights: 0.04098355025053024
NC2 Equiangle: Features: 0.11458428700764973, Weights: 0.03245548903942108
NC3 Self-Duality: 0.5405492782592773
NC4 NCC Mismatch: 0.21350000000000002

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.113523483276367
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: 8.068493843078613
Linear Weight Rank: 180
Intra Cos: 0.02681092917919159
Inter Cos: -0.004039088264107704
Norm Quadratic Average: 13.803109169006348
Nearest Class Center Accuracy: 0.6

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7736661434173584
Linear Weight Rank: 4
Intra Cos: 0.0325554758310318
Inter Cos: -0.005894406698644161
Norm Quadratic Average: 14.2018461227417
Nearest Class Center Accuracy: 0.716

Output Layer:
Intra Cos: 0.3663186728954315
Inter Cos: -0.06766566634178162
Norm Quadratic Average: 7.47279167175293
Nearest Class Center Accuracy: 0.762

