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_0.0005.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.697395324707031
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: 8.636495590209961
Linear Weight Rank: 179
Intra Cos: 0.030373165383934975
Inter Cos: -0.005144856870174408
Norm Quadratic Average: 5.2483673095703125
Nearest Class Center Accuracy: 0.611125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.558358669281006
Linear Weight Rank: 4
Intra Cos: 0.12505300343036652
Inter Cos: -0.02149875834584236
Norm Quadratic Average: 3.1229403018951416
Nearest Class Center Accuracy: 0.73575

Output Layer:
Intra Cos: 0.3683285713195801
Inter Cos: -0.07578767836093903
Norm Quadratic Average: 3.7042627334594727
Nearest Class Center Accuracy: 0.7585

Test Set:
Average Loss: 0.6564514808654786
Accuracy: 0.7315
NC1 Within Class Collapse: 5.465935707092285
NC2 Equinorm: Features: 0.12136747688055038, Weights: 0.05590076372027397
NC2 Equiangle: Features: 0.17530028025309244, Weights: 0.028384774923324585
NC3 Self-Duality: 0.222655788064003
NC4 NCC Mismatch: 0.11150000000000004

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.697395324707031
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: 8.636495590209961
Linear Weight Rank: 179
Intra Cos: 0.02804570645093918
Inter Cos: -0.0035186908207833767
Norm Quadratic Average: 5.238126277923584
Nearest Class Center Accuracy: 0.612

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.558358669281006
Linear Weight Rank: 4
Intra Cos: 0.10945823043584824
Inter Cos: -0.007894986309111118
Norm Quadratic Average: 3.1039164066314697
Nearest Class Center Accuracy: 0.7105

Output Layer:
Intra Cos: 0.3397753834724426
Inter Cos: -0.04954657331109047
Norm Quadratic Average: 3.671093702316284
Nearest Class Center Accuracy: 0.7295

