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_0.01.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.802474498748779
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: 5.945954322814941
Linear Weight Rank: 179
Intra Cos: 0.24417629837989807
Inter Cos: 0.0036743059754371643
Norm Quadratic Average: 3.744278907775879
Nearest Class Center Accuracy: 0.972

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4454567432403564
Linear Weight Rank: 4
Intra Cos: 0.6756593585014343
Inter Cos: 0.03469182178378105
Norm Quadratic Average: 4.502113342285156
Nearest Class Center Accuracy: 0.976375

Output Layer:
Intra Cos: 0.7997564077377319
Inter Cos: 0.043287575244903564
Norm Quadratic Average: 10.042713165283203
Nearest Class Center Accuracy: 0.9765

Test Set:
Average Loss: 0.13156496381759644
Accuracy: 0.9825
NC1 Within Class Collapse: 2.667670249938965
NC2 Equinorm: Features: 0.03856277093291283, Weights: 0.01706065982580185
NC2 Equiangle: Features: 0.43407591183980304, Weights: 0.40648508071899414
NC3 Self-Duality: 0.032619647681713104
NC4 NCC Mismatch: 0.02749999999999997

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.802474498748779
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: 5.945954322814941
Linear Weight Rank: 179
Intra Cos: 0.24092984199523926
Inter Cos: 0.011339403688907623
Norm Quadratic Average: 3.754631519317627
Nearest Class Center Accuracy: 0.9645

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4454567432403564
Linear Weight Rank: 4
Intra Cos: 0.6685335040092468
Inter Cos: 0.0573660284280777
Norm Quadratic Average: 4.546197414398193
Nearest Class Center Accuracy: 0.972

Output Layer:
Intra Cos: 0.7932747006416321
Inter Cos: 0.06933489441871643
Norm Quadratic Average: 10.131290435791016
Nearest Class Center Accuracy: 0.9745

