Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_265358_weight_decay_0.001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.922416687011719
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: 7.879542827606201
Linear Weight Rank: 180
Intra Cos: 0.030078930780291557
Inter Cos: -0.004149605054408312
Norm Quadratic Average: 13.468426704406738
Nearest Class Center Accuracy: 0.59675

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7442378997802734
Linear Weight Rank: 4
Intra Cos: 0.043759383261203766
Inter Cos: -0.009865513071417809
Norm Quadratic Average: 13.868072509765625
Nearest Class Center Accuracy: 0.822375

Output Layer:
Intra Cos: 0.5678400993347168
Inter Cos: -0.13675355911254883
Norm Quadratic Average: 7.510721206665039
Nearest Class Center Accuracy: 0.981625

Test Set:
Average Loss: 0.6213159255981445
Accuracy: 0.766
NC1 Within Class Collapse: 5.110445976257324
NC2 Equinorm: Features: 0.11370661109685898, Weights: 0.04027930274605751
NC2 Equiangle: Features: 0.11389633019765218, Weights: 0.03158636391162872
NC3 Self-Duality: 0.5275506377220154
NC4 NCC Mismatch: 0.20850000000000002

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.922416687011719
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: 7.879542827606201
Linear Weight Rank: 180
Intra Cos: 0.026888374239206314
Inter Cos: -0.004131800960749388
Norm Quadratic Average: 13.474221229553223
Nearest Class Center Accuracy: 0.5995

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.7442378997802734
Linear Weight Rank: 4
Intra Cos: 0.03338775411248207
Inter Cos: -0.0060197701677680016
Norm Quadratic Average: 13.883099555969238
Nearest Class Center Accuracy: 0.7215

Output Layer:
Intra Cos: 0.36671730875968933
Inter Cos: -0.06744499504566193
Norm Quadratic Average: 7.374247074127197
Nearest Class Center Accuracy: 0.762

