Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_epochs_200_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_314159_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.076364517211914
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222447380423546
Norm Quadratic Average: 3.9938881397247314
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.137821197509766
Linear Weight Rank: 179
Intra Cos: 0.026904871687293053
Inter Cos: -0.004350458271801472
Norm Quadratic Average: 13.967795372009277
Nearest Class Center Accuracy: 0.589

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.914020299911499
Linear Weight Rank: 4
Intra Cos: 0.043326109647750854
Inter Cos: -0.008585306815803051
Norm Quadratic Average: 14.396212577819824
Nearest Class Center Accuracy: 0.8065

Output Layer:
Intra Cos: 0.5749883651733398
Inter Cos: -0.09756041318178177
Norm Quadratic Average: 7.977040767669678
Nearest Class Center Accuracy: 0.985

Test Set:
Average Loss: 0.6484786891937255
Accuracy: 0.7585
NC1 Within Class Collapse: 5.362020969390869
NC2 Equinorm: Features: 0.1365322470664978, Weights: 0.04965389519929886
NC2 Equiangle: Features: 0.13965627551078796, Weights: 0.032303636272748314
NC3 Self-Duality: 0.5855067372322083
NC4 NCC Mismatch: 0.254

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.076364517211914
Linear Weight Rank: 16
Intra Cos: 0.030431464314460754
Inter Cos: -0.004549724981188774
Norm Quadratic Average: 3.995159864425659
Nearest Class Center Accuracy: 0.583

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.137821197509766
Linear Weight Rank: 179
Intra Cos: 0.026359057053923607
Inter Cos: -0.00371358054690063
Norm Quadratic Average: 14.031085968017578
Nearest Class Center Accuracy: 0.5805

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.914020299911499
Linear Weight Rank: 4
Intra Cos: 0.032363731414079666
Inter Cos: -0.003610474057495594
Norm Quadratic Average: 14.446173667907715
Nearest Class Center Accuracy: 0.6915

Output Layer:
Intra Cos: 0.37038734555244446
Inter Cos: -0.045655637979507446
Norm Quadratic Average: 7.821094036102295
Nearest Class Center Accuracy: 0.75

