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_0.0005.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.784104347229004
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: 8.833351135253906
Linear Weight Rank: 179
Intra Cos: 0.17101669311523438
Inter Cos: 0.004771587438881397
Norm Quadratic Average: 5.5200910568237305
Nearest Class Center Accuracy: 0.94425

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.049070835113525
Linear Weight Rank: 4
Intra Cos: 0.5983626246452332
Inter Cos: 0.02266906015574932
Norm Quadratic Average: 6.970934867858887
Nearest Class Center Accuracy: 0.959625

Output Layer:
Intra Cos: 0.7773182988166809
Inter Cos: 0.03139907121658325
Norm Quadratic Average: 17.64984893798828
Nearest Class Center Accuracy: 0.9655

Test Set:
Average Loss: 0.08529998898506165
Accuracy: 0.9755
NC1 Within Class Collapse: 3.574441909790039
NC2 Equinorm: Features: 0.03851209953427315, Weights: 0.01375846192240715
NC2 Equiangle: Features: 0.43255937099456787, Weights: 0.3889644145965576
NC3 Self-Duality: 0.05812610685825348
NC4 NCC Mismatch: 0.04300000000000004

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 8.784104347229004
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: 8.833351135253906
Linear Weight Rank: 179
Intra Cos: 0.168805330991745
Inter Cos: 0.0028130868449807167
Norm Quadratic Average: 5.521081924438477
Nearest Class Center Accuracy: 0.9485

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 4.049070835113525
Linear Weight Rank: 4
Intra Cos: 0.5851843953132629
Inter Cos: 0.013532299548387527
Norm Quadratic Average: 7.015804290771484
Nearest Class Center Accuracy: 0.955

Output Layer:
Intra Cos: 0.7574383020401001
Inter Cos: 0.0100471843034029
Norm Quadratic Average: 17.761383056640625
Nearest Class Center Accuracy: 0.9565

