Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_weight_decay_0.0007.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946066349744797
Inter Cos: 0.11311888694763184
Norm Quadratic Average: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10255339741706848
Inter Cos: 0.1239742636680603
Norm Quadratic Average: 89.31997680664062
Nearest Class Center Accuracy: 0.83325

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1455456018447876
Inter Cos: 0.14146092534065247
Norm Quadratic Average: 55.457847595214844
Nearest Class Center Accuracy: 0.8485

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14463169872760773
Inter Cos: 0.13044953346252441
Norm Quadratic Average: 55.98102951049805
Nearest Class Center Accuracy: 0.86725

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1770915389060974
Inter Cos: 0.11967337876558304
Norm Quadratic Average: 33.86003494262695
Nearest Class Center Accuracy: 0.90925

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18399757146835327
Inter Cos: 0.1022062823176384
Norm Quadratic Average: 35.1523551940918
Nearest Class Center Accuracy: 0.932

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2095251977443695
Inter Cos: 0.11379209160804749
Norm Quadratic Average: 24.28719711303711
Nearest Class Center Accuracy: 0.969375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2959912419319153
Inter Cos: 0.11783312261104584
Norm Quadratic Average: 18.832611083984375
Nearest Class Center Accuracy: 0.99525

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.03246307373047
Linear Weight Rank: 4031
Intra Cos: 0.48641106486320496
Inter Cos: 0.13287165760993958
Norm Quadratic Average: 116.71156311035156
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.624061584472656
Linear Weight Rank: 3671
Intra Cos: 0.6316487193107605
Inter Cos: 0.16581544280052185
Norm Quadratic Average: 62.272579193115234
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.251889228820801
Linear Weight Rank: 10
Intra Cos: 0.7571085691452026
Inter Cos: 0.19695305824279785
Norm Quadratic Average: 39.37665557861328
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9101471900939941
Inter Cos: 0.25751593708992004
Norm Quadratic Average: 21.123291015625
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.0958197569847107
Accuracy: 0.975
NC1 Within Class Collapse: 1.6496036052703857
NC2 Equinorm: Features: 0.06636273860931396, Weights: 0.012289647944271564
NC2 Equiangle: Features: 0.2130289077758789, Weights: 0.08629156748453776
NC3 Self-Duality: 0.6380095481872559
NC4 NCC Mismatch: 0.009000000000000008

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957792937755585
Norm Quadratic Average: 22.82430076599121
Nearest Class Center Accuracy: 0.809

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12728744745254517
Inter Cos: 0.13347554206848145
Norm Quadratic Average: 88.29486846923828
Nearest Class Center Accuracy: 0.827

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15567313134670258
Inter Cos: 0.15792785584926605
Norm Quadratic Average: 55.229637145996094
Nearest Class Center Accuracy: 0.844

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1515597105026245
Inter Cos: 0.13856425881385803
Norm Quadratic Average: 55.69035339355469
Nearest Class Center Accuracy: 0.862

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17019407451152802
Inter Cos: 0.12188279628753662
Norm Quadratic Average: 33.778663635253906
Nearest Class Center Accuracy: 0.903

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17678005993366241
Inter Cos: 0.10794414579868317
Norm Quadratic Average: 35.139583587646484
Nearest Class Center Accuracy: 0.9255

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2086929976940155
Inter Cos: 0.11844838410615921
Norm Quadratic Average: 24.238964080810547
Nearest Class Center Accuracy: 0.946

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26242953538894653
Inter Cos: 0.11944429576396942
Norm Quadratic Average: 18.68406867980957
Nearest Class Center Accuracy: 0.9655

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.03246307373047
Linear Weight Rank: 4031
Intra Cos: 0.42181554436683655
Inter Cos: 0.13550646603107452
Norm Quadratic Average: 113.99501037597656
Nearest Class Center Accuracy: 0.9705

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.624061584472656
Linear Weight Rank: 3671
Intra Cos: 0.5489874482154846
Inter Cos: 0.1715308278799057
Norm Quadratic Average: 60.426395416259766
Nearest Class Center Accuracy: 0.9715

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.251889228820801
Linear Weight Rank: 10
Intra Cos: 0.6561897397041321
Inter Cos: 0.20619577169418335
Norm Quadratic Average: 38.0579948425293
Nearest Class Center Accuracy: 0.9725

Output Layer:
Intra Cos: 0.801167368888855
Inter Cos: 0.2892536520957947
Norm Quadratic Average: 20.314306259155273
Nearest Class Center Accuracy: 0.971

