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_0.03.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.9499199390411377
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: 3.0080325603485107
Linear Weight Rank: 178
Intra Cos: 0.06978436559438705
Inter Cos: -0.007744565140455961
Norm Quadratic Average: 1.919024109840393
Nearest Class Center Accuracy: 0.619125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.3665823936462402
Linear Weight Rank: 4
Intra Cos: 0.22042788565158844
Inter Cos: -0.020442809909582138
Norm Quadratic Average: 1.318889856338501
Nearest Class Center Accuracy: 0.636625

Output Layer:
Intra Cos: 0.24145182967185974
Inter Cos: -0.010549914091825485
Norm Quadratic Average: 1.7594548463821411
Nearest Class Center Accuracy: 0.630875

Test Set:
Average Loss: 0.9035002403259277
Accuracy: 0.633
NC1 Within Class Collapse: 7.170001983642578
NC2 Equinorm: Features: 0.16639679670333862, Weights: 0.020895719528198242
NC2 Equiangle: Features: 0.22798887888590494, Weights: 0.096843421459198
NC3 Self-Duality: 0.05602872371673584
NC4 NCC Mismatch: 0.07750000000000001

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 2.9499199390411377
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: 3.0080325603485107
Linear Weight Rank: 178
Intra Cos: 0.06419461220502853
Inter Cos: -0.0009805111913010478
Norm Quadratic Average: 1.9128812551498413
Nearest Class Center Accuracy: 0.613

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.3665823936462402
Linear Weight Rank: 4
Intra Cos: 0.1907472014427185
Inter Cos: 0.005311435088515282
Norm Quadratic Average: 1.311268925666809
Nearest Class Center Accuracy: 0.623

Output Layer:
Intra Cos: 0.20840945839881897
Inter Cos: 0.009190700948238373
Norm Quadratic Average: 1.7488535642623901
Nearest Class Center Accuracy: 0.623

