Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp3_epochs_200_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: 8.893800735473633
Linear Weight Rank: 16
Intra Cos: 0.03299567848443985
Inter Cos: -0.006222442723810673
Norm Quadratic Average: 3.9938886165618896
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 8.832467079162598
Linear Weight Rank: 179
Intra Cos: 0.030270954594016075
Inter Cos: -0.0052377693355083466
Norm Quadratic Average: 5.366179943084717
Nearest Class Center Accuracy: 0.61175

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.702644109725952
Linear Weight Rank: 4
Intra Cos: 0.1246776357293129
Inter Cos: -0.02181023545563221
Norm Quadratic Average: 3.2490835189819336
Nearest Class Center Accuracy: 0.744375

Output Layer:
Intra Cos: 0.37084823846817017
Inter Cos: -0.08105546236038208
Norm Quadratic Average: 3.9400081634521484
Nearest Class Center Accuracy: 0.767875

Test Set:
Average Loss: 0.6407699871063233
Accuracy: 0.7365
NC1 Within Class Collapse: 5.354909896850586
NC2 Equinorm: Features: 0.11842139810323715, Weights: 0.05460747703909874
NC2 Equiangle: Features: 0.172751784324646, Weights: 0.027635003129641216
NC3 Self-Duality: 0.22619383037090302
NC4 NCC Mismatch: 0.11199999999999999

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.893800735473633
Linear Weight Rank: 16
Intra Cos: 0.030431464314460754
Inter Cos: -0.00454972218722105
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: 8.832467079162598
Linear Weight Rank: 179
Intra Cos: 0.027928974479436874
Inter Cos: -0.0036325668916106224
Norm Quadratic Average: 5.355724334716797
Nearest Class Center Accuracy: 0.611

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.702644109725952
Linear Weight Rank: 4
Intra Cos: 0.10909812152385712
Inter Cos: -0.00852169468998909
Norm Quadratic Average: 3.2296347618103027
Nearest Class Center Accuracy: 0.7155

Output Layer:
Intra Cos: 0.34017255902290344
Inter Cos: -0.05190849304199219
Norm Quadratic Average: 3.905182361602783
Nearest Class Center Accuracy: 0.74

