Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp3_epochs_100_lr_0.001_model_depth_MLP_6_model_type_MLP_rand_seed_265358_weight_decay_0.03.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.9566127061843872
Linear Weight Rank: 16
Intra Cos: 0.03299567475914955
Inter Cos: -0.006222445052117109
Norm Quadratic Average: 3.9938881397247314
Nearest Class Center Accuracy: 0.583375

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 1.9313466548919678
Linear Weight Rank: 179
Intra Cos: 0.028715766966342926
Inter Cos: -0.003937819041311741
Norm Quadratic Average: 1.1473771333694458
Nearest Class Center Accuracy: 0.57775

Layer 2: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 1.9269604682922363
Linear Weight Rank: 179
Intra Cos: 0.03109312243759632
Inter Cos: -0.004721843637526035
Norm Quadratic Average: 0.1088821291923523
Nearest Class Center Accuracy: 0.536875

Layer 3: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 1.9329110383987427
Linear Weight Rank: 180
Intra Cos: 0.03203100711107254
Inter Cos: -1.400678797836008e-06
Norm Quadratic Average: 0.010378848761320114
Nearest Class Center Accuracy: 0.529875

Layer 4: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 1.9262572526931763
Linear Weight Rank: 180
Intra Cos: 0.03765573352575302
Inter Cos: 0.006501107010990381
Norm Quadratic Average: 0.0010024067014455795
Nearest Class Center Accuracy: 0.512625

Layer 5: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 0.2855692505836487
Linear Weight Rank: 4
Intra Cos: 0.041509080678224564
Inter Cos: 0.013344264589250088
Norm Quadratic Average: 0.00010310016659786925
Nearest Class Center Accuracy: 0.4995

Output Layer:
Intra Cos: 0.0947556421160698
Inter Cos: 0.04046370089054108
Norm Quadratic Average: 3.5094319628115045e-06
Nearest Class Center Accuracy: 0.47

Test Set:
Average Loss: 1.3861978263854982
Accuracy: 0.255
NC1 Within Class Collapse: 18.467287063598633
NC2 Equinorm: Features: 0.10325036197900772, Weights: 0.04962379112839699
NC2 Equiangle: Features: 0.3482378323872884, Weights: 0.27049891153971356
NC3 Self-Duality: 1.4292584657669067
NC4 NCC Mismatch: 0.7130000000000001

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 1.9566127061843872
Linear Weight Rank: 16
Intra Cos: 0.030431468039751053
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: 1.9313466548919678
Linear Weight Rank: 179
Intra Cos: 0.02599613554775715
Inter Cos: -0.003660229267552495
Norm Quadratic Average: 1.1490254402160645
Nearest Class Center Accuracy: 0.582

Layer 2: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 1.9269604682922363
Linear Weight Rank: 179
Intra Cos: 0.028274280950427055
Inter Cos: -0.003936056979000568
Norm Quadratic Average: 0.10892269015312195
Nearest Class Center Accuracy: 0.5315

Layer 3: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 1.9329110383987427
Linear Weight Rank: 180
Intra Cos: 0.027421941980719566
Inter Cos: -0.0007107813144102693
Norm Quadratic Average: 0.010353956371545792
Nearest Class Center Accuracy: 0.5445

Layer 4: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 1.9262572526931763
Linear Weight Rank: 180
Intra Cos: 0.03140263259410858
Inter Cos: 0.004857775289565325
Norm Quadratic Average: 0.0009987266967073083
Nearest Class Center Accuracy: 0.5135

Layer 5: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 0.2855692505836487
Linear Weight Rank: 4
Intra Cos: 0.03184985741972923
Inter Cos: 0.010363857261836529
Norm Quadratic Average: 0.00010274515807395801
Nearest Class Center Accuracy: 0.487

Output Layer:
Intra Cos: 0.07328013330698013
Inter Cos: 0.04753747582435608
Norm Quadratic Average: 3.486511786832125e-06
Nearest Class Center Accuracy: 0.4535

