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_265358_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.884469985961914
Linear Weight Rank: 16
Intra Cos: 0.03299568220973015
Inter Cos: -0.006222444586455822
Norm Quadratic Average: 3.9938879013061523
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 7.798555374145508
Linear Weight Rank: 179
Intra Cos: 0.03341926261782646
Inter Cos: -0.0030673197470605373
Norm Quadratic Average: 4.67793607711792
Nearest Class Center Accuracy: 0.620875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4430906772613525
Linear Weight Rank: 4
Intra Cos: 0.14370939135551453
Inter Cos: -0.026845425367355347
Norm Quadratic Average: 2.725217580795288
Nearest Class Center Accuracy: 0.730875

Output Layer:
Intra Cos: 0.3200210928916931
Inter Cos: -0.06831631809473038
Norm Quadratic Average: 3.530242681503296
Nearest Class Center Accuracy: 0.747625

Test Set:
Average Loss: 0.6668583526611328
Accuracy: 0.7265
NC1 Within Class Collapse: 5.462140083312988
NC2 Equinorm: Features: 0.13140851259231567, Weights: 0.046907246112823486
NC2 Equiangle: Features: 0.18910094102223715, Weights: 0.03792674342791239
NC3 Self-Duality: 0.17384487390518188
NC4 NCC Mismatch: 0.09650000000000003

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.884469985961914
Linear Weight Rank: 16
Intra Cos: 0.030431464314460754
Inter Cos: -0.004549724515527487
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: 7.798555374145508
Linear Weight Rank: 179
Intra Cos: 0.029643092304468155
Inter Cos: -0.003066528821364045
Norm Quadratic Average: 4.676397800445557
Nearest Class Center Accuracy: 0.618

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4430906772613525
Linear Weight Rank: 4
Intra Cos: 0.12844081223011017
Inter Cos: -0.013044219464063644
Norm Quadratic Average: 2.7163383960723877
Nearest Class Center Accuracy: 0.7095

Output Layer:
Intra Cos: 0.2934667766094208
Inter Cos: -0.04640061408281326
Norm Quadratic Average: 3.5150063037872314
Nearest Class Center Accuracy: 0.721

