Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_979323_weight_decay_0.007.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 6.628772258758545
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: 6.590947151184082
Linear Weight Rank: 179
Intra Cos: 0.03374354913830757
Inter Cos: -0.005070514045655727
Norm Quadratic Average: 4.020334243774414
Nearest Class Center Accuracy: 0.620625

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.211864471435547
Linear Weight Rank: 4
Intra Cos: 0.17439407110214233
Inter Cos: -0.029138363897800446
Norm Quadratic Average: 2.2195956707000732
Nearest Class Center Accuracy: 0.723

Output Layer:
Intra Cos: 0.35629522800445557
Inter Cos: -0.05828208476305008
Norm Quadratic Average: 3.018409490585327
Nearest Class Center Accuracy: 0.7315

Test Set:
Average Loss: 0.7056953601837158
Accuracy: 0.7205
NC1 Within Class Collapse: 5.513795375823975
NC2 Equinorm: Features: 0.13746924698352814, Weights: 0.052841752767562866
NC2 Equiangle: Features: 0.18970425923665366, Weights: 0.02529396116733551
NC3 Self-Duality: 0.14075878262519836
NC4 NCC Mismatch: 0.08899999999999997

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 6.628772258758545
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: 6.590947151184082
Linear Weight Rank: 179
Intra Cos: 0.031001701951026917
Inter Cos: -0.0029232166707515717
Norm Quadratic Average: 4.012298583984375
Nearest Class Center Accuracy: 0.614

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.211864471435547
Linear Weight Rank: 4
Intra Cos: 0.15294811129570007
Inter Cos: -0.008477047085762024
Norm Quadratic Average: 2.203578472137451
Nearest Class Center Accuracy: 0.7005

Output Layer:
Intra Cos: 0.31896746158599854
Inter Cos: -0.03845655173063278
Norm Quadratic Average: 2.9936764240264893
Nearest Class Center Accuracy: 0.7085

