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_265358_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.901144027709961
Linear Weight Rank: 16
Intra Cos: 0.07988916337490082
Inter Cos: 0.0017584804445505142
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: 7.932146072387695
Linear Weight Rank: 179
Intra Cos: 0.19094479084014893
Inter Cos: 0.006673928815871477
Norm Quadratic Average: 4.926499843597412
Nearest Class Center Accuracy: 0.959875

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.87226939201355
Linear Weight Rank: 4
Intra Cos: 0.6435688138008118
Inter Cos: 0.03299257531762123
Norm Quadratic Average: 6.104086399078369
Nearest Class Center Accuracy: 0.98125

Output Layer:
Intra Cos: 0.8127871751785278
Inter Cos: 0.030625829473137856
Norm Quadratic Average: 14.910294532775879
Nearest Class Center Accuracy: 0.9825

Test Set:
Average Loss: 0.0990952272415161
Accuracy: 0.9755
NC1 Within Class Collapse: 2.69464111328125
NC2 Equinorm: Features: 0.02731958217918873, Weights: 0.02291898801922798
NC2 Equiangle: Features: 0.43178455034891766, Weights: 0.39077842235565186
NC3 Self-Duality: 0.04760051518678665
NC4 NCC Mismatch: 0.026499999999999968

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 7.901144027709961
Linear Weight Rank: 16
Intra Cos: 0.0803302749991417
Inter Cos: 0.0033129025250673294
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: 7.932146072387695
Linear Weight Rank: 179
Intra Cos: 0.1920875459909439
Inter Cos: 0.004507714882493019
Norm Quadratic Average: 4.933361530303955
Nearest Class Center Accuracy: 0.96

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.87226939201355
Linear Weight Rank: 4
Intra Cos: 0.6412883996963501
Inter Cos: 0.030947677791118622
Norm Quadratic Average: 6.159020900726318
Nearest Class Center Accuracy: 0.964

Output Layer:
Intra Cos: 0.8009024262428284
Inter Cos: 0.035568829625844955
Norm Quadratic Average: 15.03050708770752
Nearest Class Center Accuracy: 0.971

