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_0.02.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 4.047059535980225
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: 4.058605670928955
Linear Weight Rank: 178
Intra Cos: 0.04867585748434067
Inter Cos: -0.005580349825322628
Norm Quadratic Average: 2.5246431827545166
Nearest Class Center Accuracy: 0.62725

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.6643309593200684
Linear Weight Rank: 4
Intra Cos: 0.23121419548988342
Inter Cos: -0.031006477773189545
Norm Quadratic Average: 1.5125991106033325
Nearest Class Center Accuracy: 0.67475

Output Layer:
Intra Cos: 0.29270580410957336
Inter Cos: -0.025661731138825417
Norm Quadratic Average: 2.161935806274414
Nearest Class Center Accuracy: 0.670375

Test Set:
Average Loss: 0.8247265815734863
Accuracy: 0.672
NC1 Within Class Collapse: 6.285557270050049
NC2 Equinorm: Features: 0.15533018112182617, Weights: 0.030449597164988518
NC2 Equiangle: Features: 0.20952296257019043, Weights: 0.06903318564097087
NC3 Self-Duality: 0.07132717967033386
NC4 NCC Mismatch: 0.08450000000000002

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 4.047059535980225
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: 4.058605670928955
Linear Weight Rank: 178
Intra Cos: 0.04466980695724487
Inter Cos: -0.0014365818351507187
Norm Quadratic Average: 2.517899751663208
Nearest Class Center Accuracy: 0.6175

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.6643309593200684
Linear Weight Rank: 4
Intra Cos: 0.200632244348526
Inter Cos: -0.005189855117350817
Norm Quadratic Average: 1.5019705295562744
Nearest Class Center Accuracy: 0.66

Output Layer:
Intra Cos: 0.2490033358335495
Inter Cos: -0.011851450428366661
Norm Quadratic Average: 2.1471681594848633
Nearest Class Center Accuracy: 0.6515

