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_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.877887725830078
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: 8.972123146057129
Linear Weight Rank: 179
Intra Cos: 0.17183354496955872
Inter Cos: 0.006125946529209614
Norm Quadratic Average: 5.545636177062988
Nearest Class Center Accuracy: 0.958875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.0783305168151855
Linear Weight Rank: 4
Intra Cos: 0.6095802187919617
Inter Cos: 0.027814697474241257
Norm Quadratic Average: 7.003490924835205
Nearest Class Center Accuracy: 0.97275

Output Layer:
Intra Cos: 0.7900493144989014
Inter Cos: 0.03993774950504303
Norm Quadratic Average: 17.8721923828125
Nearest Class Center Accuracy: 0.973625

Test Set:
Average Loss: 0.08552108597755433
Accuracy: 0.979
NC1 Within Class Collapse: 2.980861186981201
NC2 Equinorm: Features: 0.038534920662641525, Weights: 0.01659860461950302
NC2 Equiangle: Features: 0.4345155159632365, Weights: 0.39402135213216144
NC3 Self-Duality: 0.056163590401411057
NC4 NCC Mismatch: 0.030000000000000027

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.877887725830078
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: 8.972123146057129
Linear Weight Rank: 179
Intra Cos: 0.16912612318992615
Inter Cos: 0.006645007058978081
Norm Quadratic Average: 5.553534507751465
Nearest Class Center Accuracy: 0.9525

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.0783305168151855
Linear Weight Rank: 4
Intra Cos: 0.6020039319992065
Inter Cos: 0.049495015293359756
Norm Quadratic Average: 7.072723388671875
Nearest Class Center Accuracy: 0.964

Output Layer:
Intra Cos: 0.7802425026893616
Inter Cos: 0.06684672832489014
Norm Quadratic Average: 18.049272537231445
Nearest Class Center Accuracy: 0.967

