Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_conic_epochs_200_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_979323_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.799004077911377
Linear Weight Rank: 16
Intra Cos: 0.07988917827606201
Inter Cos: 0.001758486032485962
Norm Quadratic Average: 4.001680374145508
Nearest Class Center Accuracy: 0.948875

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.912342548370361
Linear Weight Rank: 179
Intra Cos: 0.23925432562828064
Inter Cos: 0.006280979141592979
Norm Quadratic Average: 3.758192300796509
Nearest Class Center Accuracy: 0.95125

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4398348331451416
Linear Weight Rank: 4
Intra Cos: 0.6572802662849426
Inter Cos: 0.029846256598830223
Norm Quadratic Average: 4.526331424713135
Nearest Class Center Accuracy: 0.960875

Output Layer:
Intra Cos: 0.7854360342025757
Inter Cos: 0.03276229277253151
Norm Quadratic Average: 10.038217544555664
Nearest Class Center Accuracy: 0.96725

Test Set:
Average Loss: 0.1317697081565857
Accuracy: 0.9835
NC1 Within Class Collapse: 3.2082748413085938
NC2 Equinorm: Features: 0.0349130779504776, Weights: 0.01206564623862505
NC2 Equiangle: Features: 0.43202924728393555, Weights: 0.4011770486831665
NC3 Self-Duality: 0.03583597019314766
NC4 NCC Mismatch: 0.038000000000000034

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.799004077911377
Linear Weight Rank: 16
Intra Cos: 0.08033028244972229
Inter Cos: 0.003312898799777031
Norm Quadratic Average: 3.9883358478546143
Nearest Class Center Accuracy: 0.9165

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.912342548370361
Linear Weight Rank: 179
Intra Cos: 0.23658327758312225
Inter Cos: 0.003497038036584854
Norm Quadratic Average: 3.7641706466674805
Nearest Class Center Accuracy: 0.951

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.4398348331451416
Linear Weight Rank: 4
Intra Cos: 0.6430407762527466
Inter Cos: 0.01892714388668537
Norm Quadratic Average: 4.556868076324463
Nearest Class Center Accuracy: 0.9585

Output Layer:
Intra Cos: 0.7745447158813477
Inter Cos: 0.012452082708477974
Norm Quadratic Average: 10.098179817199707
Nearest Class Center Accuracy: 0.963

