Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01989092119038105
Inter Cos: 0.10477276146411896
Norm Quadratic Average: 27.59718132019043
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01878073625266552
Inter Cos: 0.06878403574228287
Norm Quadratic Average: 6.455831050872803
Nearest Class Center Accuracy: 0.40208

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.019533418118953705
Inter Cos: 0.05068562552332878
Norm Quadratic Average: 3.126890182495117
Nearest Class Center Accuracy: 0.53826

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.014480910263955593
Inter Cos: 0.041598137468099594
Norm Quadratic Average: 2.297811508178711
Nearest Class Center Accuracy: 0.61608

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020266951993107796
Inter Cos: 0.03723035752773285
Norm Quadratic Average: 1.5407660007476807
Nearest Class Center Accuracy: 0.7636

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03748101368546486
Inter Cos: 0.04309697449207306
Norm Quadratic Average: 1.034059762954712
Nearest Class Center Accuracy: 0.88614

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2120063602924347
Inter Cos: 0.1279638707637787
Norm Quadratic Average: 0.7245470881462097
Nearest Class Center Accuracy: 0.9873

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7861854434013367
Inter Cos: 0.10581847280263901
Norm Quadratic Average: 0.8447202444076538
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.306746244430542
Linear Weight Rank: 2866
Intra Cos: 0.9737449288368225
Inter Cos: 0.0059767416678369045
Norm Quadratic Average: 23.625972747802734
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.3521108627319336
Linear Weight Rank: 856
Intra Cos: 0.985371470451355
Inter Cos: 0.04400600120425224
Norm Quadratic Average: 16.734140396118164
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2962188720703125
Linear Weight Rank: 9
Intra Cos: 0.987634003162384
Inter Cos: 0.07926107943058014
Norm Quadratic Average: 12.193192481994629
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9906390309333801
Inter Cos: 0.11668998003005981
Norm Quadratic Average: 9.317414283752441
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.4678637077331543
Accuracy: 0.8618
NC1 Within Class Collapse: 3.4465999603271484
NC2 Equinorm: Features: 0.1337757557630539, Weights: 0.006970366463065147
NC2 Equiangle: Features: 0.12961262596978082, Weights: 0.021981571780310738
NC3 Self-Duality: 0.05871683731675148
NC4 NCC Mismatch: 0.020399999999999974

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018526073545217514
Inter Cos: 0.1042705774307251
Norm Quadratic Average: 27.550134658813477
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017657382413744926
Inter Cos: 0.07027945667505264
Norm Quadratic Average: 6.451247215270996
Nearest Class Center Accuracy: 0.4226

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018481602892279625
Inter Cos: 0.051860421895980835
Norm Quadratic Average: 3.128462076187134
Nearest Class Center Accuracy: 0.5506

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013510189019143581
Inter Cos: 0.04249943047761917
Norm Quadratic Average: 2.3015236854553223
Nearest Class Center Accuracy: 0.6213

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01723320223391056
Inter Cos: 0.03759356215596199
Norm Quadratic Average: 1.540985107421875
Nearest Class Center Accuracy: 0.727

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.027874119579792023
Inter Cos: 0.04553995281457901
Norm Quadratic Average: 1.0259497165679932
Nearest Class Center Accuracy: 0.7851

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14576146006584167
Inter Cos: 0.14061693847179413
Norm Quadratic Average: 0.702896237373352
Nearest Class Center Accuracy: 0.8255

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.41986581683158875
Inter Cos: 0.21988871693611145
Norm Quadratic Average: 0.7726455926895142
Nearest Class Center Accuracy: 0.8587

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.306746244430542
Linear Weight Rank: 2866
Intra Cos: 0.5598146915435791
Inter Cos: 0.2429509162902832
Norm Quadratic Average: 20.686546325683594
Nearest Class Center Accuracy: 0.8594

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.3521108627319336
Linear Weight Rank: 856
Intra Cos: 0.5764195322990417
Inter Cos: 0.2572129964828491
Norm Quadratic Average: 14.606115341186523
Nearest Class Center Accuracy: 0.8602

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2962188720703125
Linear Weight Rank: 9
Intra Cos: 0.5813471078872681
Inter Cos: 0.26861903071403503
Norm Quadratic Average: 10.652215957641602
Nearest Class Center Accuracy: 0.8603

Output Layer:
Intra Cos: 0.5967015624046326
Inter Cos: 0.2893829345703125
Norm Quadratic Average: 8.146553993225098
Nearest Class Center Accuracy: 0.8606

