Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_weight_decay_0.005.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.021450400352478027
Inter Cos: 0.11371058970689774
Norm Quadratic Average: 27.691621780395508
Nearest Class Center Accuracy: 0.279125

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02725406549870968
Inter Cos: 0.1042475700378418
Norm Quadratic Average: 68.5009536743164
Nearest Class Center Accuracy: 0.337125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03153383731842041
Inter Cos: 0.09409790486097336
Norm Quadratic Average: 49.977745056152344
Nearest Class Center Accuracy: 0.370125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.027216250076889992
Inter Cos: 0.07310889661312103
Norm Quadratic Average: 54.28013610839844
Nearest Class Center Accuracy: 0.403

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03579184412956238
Inter Cos: 0.08034537732601166
Norm Quadratic Average: 34.550453186035156
Nearest Class Center Accuracy: 0.42825

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03408083692193031
Inter Cos: 0.06613661348819733
Norm Quadratic Average: 35.30657196044922
Nearest Class Center Accuracy: 0.47475

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.048091936856508255
Inter Cos: 0.07597433030605316
Norm Quadratic Average: 22.808366775512695
Nearest Class Center Accuracy: 0.583625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06805925816297531
Inter Cos: 0.07560789585113525
Norm Quadratic Average: 16.0484561920166
Nearest Class Center Accuracy: 0.899125

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.766845703125
Linear Weight Rank: 4031
Intra Cos: 0.22412583231925964
Inter Cos: 0.11774766445159912
Norm Quadratic Average: 88.23064422607422
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.256919860839844
Linear Weight Rank: 3671
Intra Cos: 0.5197762846946716
Inter Cos: 0.21781963109970093
Norm Quadratic Average: 43.111446380615234
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.148399591445923
Linear Weight Rank: 10
Intra Cos: 0.75252366065979
Inter Cos: 0.3023163080215454
Norm Quadratic Average: 28.498777389526367
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8928646445274353
Inter Cos: 0.4931694269180298
Norm Quadratic Average: 18.584543228149414
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 1.8598439102172852
Accuracy: 0.592
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.20542563498020172, Weights: 0.01860719919204712
NC2 Equiangle: Features: 0.44760797288682724, Weights: 0.0936239136589898
NC3 Self-Duality: 0.5788381695747375
NC4 NCC Mismatch: 0.14600000000000002

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018480459228157997
Inter Cos: 0.09352368116378784
Norm Quadratic Average: 27.530664443969727
Nearest Class Center Accuracy: 0.2895

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.024941980838775635
Inter Cos: 0.0916694849729538
Norm Quadratic Average: 68.50816345214844
Nearest Class Center Accuracy: 0.3525

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.029964448884129524
Inter Cos: 0.09137305617332458
Norm Quadratic Average: 49.98686981201172
Nearest Class Center Accuracy: 0.392

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.026871798560023308
Inter Cos: 0.06883493810892105
Norm Quadratic Average: 54.34891128540039
Nearest Class Center Accuracy: 0.4235

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03334340825676918
Inter Cos: 0.0816689133644104
Norm Quadratic Average: 34.54233932495117
Nearest Class Center Accuracy: 0.4465

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.030336065217852592
Inter Cos: 0.06289757788181305
Norm Quadratic Average: 35.25603485107422
Nearest Class Center Accuracy: 0.4835

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03487246483564377
Inter Cos: 0.07254712283611298
Norm Quadratic Average: 22.741165161132812
Nearest Class Center Accuracy: 0.5035

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.035636115819215775
Inter Cos: 0.07280649989843369
Norm Quadratic Average: 15.912775039672852
Nearest Class Center Accuracy: 0.5825

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.766845703125
Linear Weight Rank: 4031
Intra Cos: 0.0672592967748642
Inter Cos: 0.11480522900819778
Norm Quadratic Average: 84.49296569824219
Nearest Class Center Accuracy: 0.62

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.256919860839844
Linear Weight Rank: 3671
Intra Cos: 0.14707396924495697
Inter Cos: 0.22746849060058594
Norm Quadratic Average: 39.133270263671875
Nearest Class Center Accuracy: 0.5945

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.148399591445923
Linear Weight Rank: 10
Intra Cos: 0.2173512727022171
Inter Cos: 0.34206339716911316
Norm Quadratic Average: 24.948768615722656
Nearest Class Center Accuracy: 0.5855

Output Layer:
Intra Cos: 0.2836761772632599
Inter Cos: 0.4766177535057068
Norm Quadratic Average: 15.962656021118164
Nearest Class Center Accuracy: 0.57

