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_0.01.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.163584232330322
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: 5.159295082092285
Linear Weight Rank: 179
Intra Cos: 0.03073846362531185
Inter Cos: -0.00398654118180275
Norm Quadratic Average: 8.73233699798584
Nearest Class Center Accuracy: 0.601625

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.311734437942505
Linear Weight Rank: 4
Intra Cos: 0.06590846180915833
Inter Cos: -0.014117765240371227
Norm Quadratic Average: 9.258179664611816
Nearest Class Center Accuracy: 0.915625

Output Layer:
Intra Cos: 0.6144455671310425
Inter Cos: -0.1509390026330948
Norm Quadratic Average: 5.823510646820068
Nearest Class Center Accuracy: 0.9815

Test Set:
Average Loss: 0.5770681781768798
Accuracy: 0.7685
NC1 Within Class Collapse: 3.995370864868164
NC2 Equinorm: Features: 0.12079489976167679, Weights: 0.03898824006319046
NC2 Equiangle: Features: 0.11839769283930461, Weights: 0.021868969003359478
NC3 Self-Duality: 0.3328808844089508
NC4 NCC Mismatch: 0.11699999999999999

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.163584232330322
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: 5.159295082092285
Linear Weight Rank: 179
Intra Cos: 0.0272696353495121
Inter Cos: -0.003924104850739241
Norm Quadratic Average: 8.7334623336792
Nearest Class Center Accuracy: 0.603

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.311734437942505
Linear Weight Rank: 4
Intra Cos: 0.04960308223962784
Inter Cos: -0.005997370462864637
Norm Quadratic Average: 9.272797584533691
Nearest Class Center Accuracy: 0.7645

Output Layer:
Intra Cos: 0.3965802788734436
Inter Cos: -0.06792717427015305
Norm Quadratic Average: 5.725356101989746
Nearest Class Center Accuracy: 0.7785

