Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp6_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_979323_weight_decay_0.0001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.495508193969727
Linear Weight Rank: 16
Intra Cos: 0.014583897776901722
Inter Cos: 0.004829857032746077
Norm Quadratic Average: 3.9931399822235107
Nearest Class Center Accuracy: 0.447

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.427787780761719
Linear Weight Rank: 179
Intra Cos: 0.014439573511481285
Inter Cos: 0.006491541862487793
Norm Quadratic Average: 5.098997116088867
Nearest Class Center Accuracy: 0.46775

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.589871644973755
Linear Weight Rank: 4
Intra Cos: 0.04035293310880661
Inter Cos: 0.01758997142314911
Norm Quadratic Average: 2.525627851486206
Nearest Class Center Accuracy: 0.526125

Output Layer:
Intra Cos: 0.17952097952365875
Inter Cos: 0.08086630702018738
Norm Quadratic Average: 1.602953553199768
Nearest Class Center Accuracy: 0.548

Test Set:
Average Loss: 1.1118702545166015
Accuracy: 0.5195
NC1 Within Class Collapse: 16.897785186767578
NC2 Equinorm: Features: 0.10911577939987183, Weights: 0.024673128500580788
NC2 Equiangle: Features: 0.3817776044209798, Weights: 0.09962071975072224
NC3 Self-Duality: 0.4110638499259949
NC4 NCC Mismatch: 0.16049999999999998

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.495508193969727
Linear Weight Rank: 16
Intra Cos: 0.014108890667557716
Inter Cos: 0.005012288689613342
Norm Quadratic Average: 3.9761204719543457
Nearest Class Center Accuracy: 0.4485

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.427787780761719
Linear Weight Rank: 179
Intra Cos: 0.013779406435787678
Inter Cos: 0.006123296916484833
Norm Quadratic Average: 5.0733323097229
Nearest Class Center Accuracy: 0.4685

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.589871644973755
Linear Weight Rank: 4
Intra Cos: 0.03486695885658264
Inter Cos: 0.017877575010061264
Norm Quadratic Average: 2.5063600540161133
Nearest Class Center Accuracy: 0.505

Output Layer:
Intra Cos: 0.14945457875728607
Inter Cos: 0.07949792593717575
Norm Quadratic Average: 1.5873749256134033
Nearest Class Center Accuracy: 0.513

