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_0.0001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.158615112304688
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: 8.221000671386719
Linear Weight Rank: 179
Intra Cos: 0.02692038007080555
Inter Cos: -0.004322605207562447
Norm Quadratic Average: 14.112407684326172
Nearest Class Center Accuracy: 0.5885

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.9275121688842773
Linear Weight Rank: 4
Intra Cos: 0.042877987027168274
Inter Cos: -0.008453980088233948
Norm Quadratic Average: 14.537243843078613
Nearest Class Center Accuracy: 0.803

Output Layer:
Intra Cos: 0.5735727548599243
Inter Cos: -0.09639769047498703
Norm Quadratic Average: 8.035816192626953
Nearest Class Center Accuracy: 0.9845

Test Set:
Average Loss: 0.6502771949768067
Accuracy: 0.759
NC1 Within Class Collapse: 5.3889570236206055
NC2 Equinorm: Features: 0.13701170682907104, Weights: 0.049577582627534866
NC2 Equiangle: Features: 0.13984779516855875, Weights: 0.03288221855958303
NC3 Self-Duality: 0.5904886722564697
NC4 NCC Mismatch: 0.258

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.158615112304688
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: 8.221000671386719
Linear Weight Rank: 179
Intra Cos: 0.02631608210504055
Inter Cos: -0.003696790896356106
Norm Quadratic Average: 14.176253318786621
Nearest Class Center Accuracy: 0.58

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.9275121688842773
Linear Weight Rank: 4
Intra Cos: 0.03226296976208687
Inter Cos: -0.003551589325070381
Norm Quadratic Average: 14.587031364440918
Nearest Class Center Accuracy: 0.6925

Output Layer:
Intra Cos: 0.3693048059940338
Inter Cos: -0.04560306295752525
Norm Quadratic Average: 7.880130290985107
Nearest Class Center Accuracy: 0.751

