Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_conic_epochs_200_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_338327_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.8559746742248535
Linear Weight Rank: 16
Intra Cos: 0.07988917827606201
Inter Cos: 0.0017584916204214096
Norm Quadratic Average: 4.001680850982666
Nearest Class Center Accuracy: 0.948875

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 7.940479755401611
Linear Weight Rank: 180
Intra Cos: 0.19298921525478363
Inter Cos: 0.002902055624872446
Norm Quadratic Average: 4.896327972412109
Nearest Class Center Accuracy: 0.9615

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.8801522254943848
Linear Weight Rank: 4
Intra Cos: 0.6547555923461914
Inter Cos: 0.024930518120527267
Norm Quadratic Average: 6.015026569366455
Nearest Class Center Accuracy: 0.982375

Output Layer:
Intra Cos: 0.8188085556030273
Inter Cos: 0.03463989496231079
Norm Quadratic Average: 14.737590789794922
Nearest Class Center Accuracy: 0.982625

Test Set:
Average Loss: 0.09765376710891724
Accuracy: 0.9835
NC1 Within Class Collapse: 2.7065300941467285
NC2 Equinorm: Features: 0.044090624898672104, Weights: 0.01719188690185547
NC2 Equiangle: Features: 0.43409470717112225, Weights: 0.39230581124623615
NC3 Self-Duality: 0.05270576477050781
NC4 NCC Mismatch: 0.026499999999999968

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.8559746742248535
Linear Weight Rank: 16
Intra Cos: 0.0803302749991417
Inter Cos: 0.0033128950744867325
Norm Quadratic Average: 3.988335609436035
Nearest Class Center Accuracy: 0.9165

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 7.940479755401611
Linear Weight Rank: 180
Intra Cos: 0.1900874525308609
Inter Cos: 0.007681151852011681
Norm Quadratic Average: 4.9031243324279785
Nearest Class Center Accuracy: 0.9555

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.8801522254943848
Linear Weight Rank: 4
Intra Cos: 0.6478388905525208
Inter Cos: 0.04889421910047531
Norm Quadratic Average: 6.077184677124023
Nearest Class Center Accuracy: 0.973

Output Layer:
Intra Cos: 0.8074399828910828
Inter Cos: 0.06348223239183426
Norm Quadratic Average: 14.881317138671875
Nearest Class Center Accuracy: 0.976

