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_846264_weight_decay_0.005.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.181178569793701
Linear Weight Rank: 16
Intra Cos: 0.07988917082548141
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: 7.295756816864014
Linear Weight Rank: 179
Intra Cos: 0.2015332132577896
Inter Cos: 0.00504625728353858
Norm Quadratic Average: 4.546128273010254
Nearest Class Center Accuracy: 0.96625

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7242953777313232
Linear Weight Rank: 4
Intra Cos: 0.6453785300254822
Inter Cos: 0.03214936703443527
Norm Quadratic Average: 5.518404483795166
Nearest Class Center Accuracy: 0.974

Output Layer:
Intra Cos: 0.7945065498352051
Inter Cos: 0.04323466867208481
Norm Quadratic Average: 13.110650062561035
Nearest Class Center Accuracy: 0.9745

Test Set:
Average Loss: 0.1069260892868042
Accuracy: 0.9795
NC1 Within Class Collapse: 2.8167405128479004
NC2 Equinorm: Features: 0.03851144388318062, Weights: 0.016722029075026512
NC2 Equiangle: Features: 0.4341801007588704, Weights: 0.40055028597513836
NC3 Self-Duality: 0.0434238500893116
NC4 NCC Mismatch: 0.030000000000000027

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.181178569793701
Linear Weight Rank: 16
Intra Cos: 0.08033028990030289
Inter Cos: 0.003312898799777031
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: 7.295756816864014
Linear Weight Rank: 179
Intra Cos: 0.19861270487308502
Inter Cos: 0.00852862186729908
Norm Quadratic Average: 4.554919719696045
Nearest Class Center Accuracy: 0.959

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7242953777313232
Linear Weight Rank: 4
Intra Cos: 0.6378946900367737
Inter Cos: 0.05484279245138168
Norm Quadratic Average: 5.5732831954956055
Nearest Class Center Accuracy: 0.9675

Output Layer:
Intra Cos: 0.7851083278656006
Inter Cos: 0.0698147788643837
Norm Quadratic Average: 13.23419189453125
Nearest Class Center Accuracy: 0.97

