Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_979323_weight_decay_0.0005.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.061079978942871
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222443655133247
Norm Quadratic Average: 3.9938876628875732
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.037186622619629
Linear Weight Rank: 180
Intra Cos: 0.025333791971206665
Inter Cos: -0.004711569286882877
Norm Quadratic Average: 13.812987327575684
Nearest Class Center Accuracy: 0.592125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.816333055496216
Linear Weight Rank: 4
Intra Cos: 0.040881212800741196
Inter Cos: -0.009266152046620846
Norm Quadratic Average: 14.226522445678711
Nearest Class Center Accuracy: 0.820125

Output Layer:
Intra Cos: 0.5581942200660706
Inter Cos: -0.11544423550367355
Norm Quadratic Average: 7.76943302154541
Nearest Class Center Accuracy: 0.980625

Test Set:
Average Loss: 0.6136332845687866
Accuracy: 0.7655
NC1 Within Class Collapse: 5.125115394592285
NC2 Equinorm: Features: 0.13284963369369507, Weights: 0.04090669006109238
NC2 Equiangle: Features: 0.14477290709813437, Weights: 0.03172105054060618
NC3 Self-Duality: 0.5192108750343323
NC4 NCC Mismatch: 0.21050000000000002

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.061079978942871
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
Inter Cos: -0.004549722652882338
Norm Quadratic Average: 3.9951601028442383
Nearest Class Center Accuracy: 0.583

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.037186622619629
Linear Weight Rank: 180
Intra Cos: 0.023191094398498535
Inter Cos: -0.003378314897418022
Norm Quadratic Average: 13.80250072479248
Nearest Class Center Accuracy: 0.6015

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.816333055496216
Linear Weight Rank: 4
Intra Cos: 0.03018159419298172
Inter Cos: -0.004582075867801905
Norm Quadratic Average: 14.215110778808594
Nearest Class Center Accuracy: 0.7185

Output Layer:
Intra Cos: 0.36562278866767883
Inter Cos: -0.053397037088871
Norm Quadratic Average: 7.6894330978393555
Nearest Class Center Accuracy: 0.768

