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_0.0003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.7720947265625
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: 8.710443496704102
Linear Weight Rank: 179
Intra Cos: 0.030292395502328873
Inter Cos: -0.005137909669429064
Norm Quadratic Average: 5.2928972244262695
Nearest Class Center Accuracy: 0.611625

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.5697021484375
Linear Weight Rank: 4
Intra Cos: 0.12357398122549057
Inter Cos: -0.02123435214161873
Norm Quadratic Average: 3.1609721183776855
Nearest Class Center Accuracy: 0.73625

Output Layer:
Intra Cos: 0.36857718229293823
Inter Cos: -0.0762437954545021
Norm Quadratic Average: 3.729062795639038
Nearest Class Center Accuracy: 0.75925

Test Set:
Average Loss: 0.6551747817993164
Accuracy: 0.7325
NC1 Within Class Collapse: 5.468110084533691
NC2 Equinorm: Features: 0.12086094170808792, Weights: 0.05586355924606323
NC2 Equiangle: Features: 0.1748454968134562, Weights: 0.02859633167584737
NC3 Self-Duality: 0.226058691740036
NC4 NCC Mismatch: 0.11250000000000004

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.7720947265625
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: 8.710443496704102
Linear Weight Rank: 179
Intra Cos: 0.027978571131825447
Inter Cos: -0.0035261206794530153
Norm Quadratic Average: 5.282604694366455
Nearest Class Center Accuracy: 0.612

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.5697021484375
Linear Weight Rank: 4
Intra Cos: 0.10817523300647736
Inter Cos: -0.007859514094889164
Norm Quadratic Average: 3.1418845653533936
Nearest Class Center Accuracy: 0.7105

Output Layer:
Intra Cos: 0.33982545137405396
Inter Cos: -0.049790699034929276
Norm Quadratic Average: 3.6956863403320312
Nearest Class Center Accuracy: 0.73

