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_979323_weight_decay_0.05.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.1814860105514526
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222443655133247
Norm Quadratic Average: 3.9938876628875732
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 1.232884168624878
Linear Weight Rank: 170
Intra Cos: 0.03514447435736656
Inter Cos: -0.005166282877326012
Norm Quadratic Average: 1.4920239448547363
Nearest Class Center Accuracy: 0.63

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.243732213973999
Linear Weight Rank: 4
Intra Cos: 0.48612621426582336
Inter Cos: -0.13537275791168213
Norm Quadratic Average: 2.2948718070983887
Nearest Class Center Accuracy: 0.8985

Output Layer:
Intra Cos: 0.6115661263465881
Inter Cos: -0.15731601417064667
Norm Quadratic Average: 2.70831036567688
Nearest Class Center Accuracy: 0.896875

Test Set:
Average Loss: 0.615153823852539
Accuracy: 0.762
NC1 Within Class Collapse: 3.023911237716675
NC2 Equinorm: Features: 0.0779404416680336, Weights: 0.023399624973535538
NC2 Equiangle: Features: 0.10204273462295532, Weights: 0.03155761460463206
NC3 Self-Duality: 0.034399956464767456
NC4 NCC Mismatch: 0.02300000000000002

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.1814860105514526
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.004549722652882338
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: 1.232884168624878
Linear Weight Rank: 170
Intra Cos: 0.030695151537656784
Inter Cos: -0.0034755091182887554
Norm Quadratic Average: 1.4910273551940918
Nearest Class Center Accuracy: 0.6095

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.243732213973999
Linear Weight Rank: 4
Intra Cos: 0.35857537388801575
Inter Cos: -0.06151611730456352
Norm Quadratic Average: 2.2796881198883057
Nearest Class Center Accuracy: 0.7655

Output Layer:
Intra Cos: 0.4440636932849884
Inter Cos: -0.07168097794055939
Norm Quadratic Average: 2.6817381381988525
Nearest Class Center Accuracy: 0.7685

