Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp6_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_314159_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.413307189941406
Linear Weight Rank: 16
Intra Cos: 0.014583898708224297
Inter Cos: 0.004829856567084789
Norm Quadratic Average: 3.993140459060669
Nearest Class Center Accuracy: 0.447

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.435484409332275
Linear Weight Rank: 179
Intra Cos: 0.01795891486108303
Inter Cos: 0.0075845601968467236
Norm Quadratic Average: 3.2650625705718994
Nearest Class Center Accuracy: 0.471875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.1392898559570312
Linear Weight Rank: 4
Intra Cos: 0.08147875964641571
Inter Cos: 0.039263371378183365
Norm Quadratic Average: 1.3987984657287598
Nearest Class Center Accuracy: 0.5125

Output Layer:
Intra Cos: 0.15778610110282898
Inter Cos: 0.09373866021633148
Norm Quadratic Average: 1.2751495838165283
Nearest Class Center Accuracy: 0.5135

Test Set:
Average Loss: 1.156408634185791
Accuracy: 0.4965
NC1 Within Class Collapse: 19.49472999572754
NC2 Equinorm: Features: 0.1021559089422226, Weights: 0.031252287328243256
NC2 Equiangle: Features: 0.4757908185323079, Weights: 0.14805461963017783
NC3 Self-Duality: 0.19600968062877655
NC4 NCC Mismatch: 0.11150000000000004

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.413307189941406
Linear Weight Rank: 16
Intra Cos: 0.014108894392848015
Inter Cos: 0.005012289620935917
Norm Quadratic Average: 3.9761204719543457
Nearest Class Center Accuracy: 0.4485

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.435484409332275
Linear Weight Rank: 179
Intra Cos: 0.019170278683304787
Inter Cos: 0.007546455133706331
Norm Quadratic Average: 3.250420570373535
Nearest Class Center Accuracy: 0.481

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.1392898559570312
Linear Weight Rank: 4
Intra Cos: 0.07788180559873581
Inter Cos: 0.03878232464194298
Norm Quadratic Average: 1.3875463008880615
Nearest Class Center Accuracy: 0.5015

Output Layer:
Intra Cos: 0.1463243067264557
Inter Cos: 0.08782479166984558
Norm Quadratic Average: 1.263469934463501
Nearest Class Center Accuracy: 0.494

