Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_weight_decay_0.02.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946067094802856
Inter Cos: 0.11311887204647064
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: 0.10593842715024948
Inter Cos: 0.1208888366818428
Norm Quadratic Average: 33.32707595825195
Nearest Class Center Accuracy: 0.825625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1464235484600067
Inter Cos: 0.1329980194568634
Norm Quadratic Average: 21.31049346923828
Nearest Class Center Accuracy: 0.847

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15399721264839172
Inter Cos: 0.13085772097110748
Norm Quadratic Average: 21.35322380065918
Nearest Class Center Accuracy: 0.873625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18613657355308533
Inter Cos: 0.11392491310834885
Norm Quadratic Average: 12.913969039916992
Nearest Class Center Accuracy: 0.9215

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2173345386981964
Inter Cos: 0.11762004345655441
Norm Quadratic Average: 13.535909652709961
Nearest Class Center Accuracy: 0.95925

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2925959825515747
Inter Cos: 0.09797415137290955
Norm Quadratic Average: 9.152750015258789
Nearest Class Center Accuracy: 0.996125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5405685901641846
Inter Cos: 0.11439734697341919
Norm Quadratic Average: 7.295119762420654
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.806793212890625
Linear Weight Rank: 4031
Intra Cos: 0.8525072336196899
Inter Cos: 0.09226247668266296
Norm Quadratic Average: 69.57170867919922
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.72426700592041
Linear Weight Rank: 3670
Intra Cos: 0.9419355988502502
Inter Cos: 0.11463458091020584
Norm Quadratic Average: 32.02964401245117
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5487462282180786
Linear Weight Rank: 10
Intra Cos: 0.9594380855560303
Inter Cos: 0.18690499663352966
Norm Quadratic Average: 17.766998291015625
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9665332436561584
Inter Cos: 0.3297680616378784
Norm Quadratic Average: 9.60421085357666
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.07042737340927124
Accuracy: 0.9815
NC1 Within Class Collapse: 1.0065696239471436
NC2 Equinorm: Features: 0.05853470414876938, Weights: 0.017455656081438065
NC2 Equiangle: Features: 0.19610375298394098, Weights: 0.08630246056450738
NC3 Self-Duality: 0.16868403553962708
NC4 NCC Mismatch: 0.0040000000000000036

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957792192697525
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: 0.12456785887479782
Inter Cos: 0.13212299346923828
Norm Quadratic Average: 32.76898956298828
Nearest Class Center Accuracy: 0.8195

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15610401332378387
Inter Cos: 0.16229495406150818
Norm Quadratic Average: 21.046403884887695
Nearest Class Center Accuracy: 0.839

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15757785737514496
Inter Cos: 0.15456639230251312
Norm Quadratic Average: 21.0779972076416
Nearest Class Center Accuracy: 0.864

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1735304892063141
Inter Cos: 0.1377221643924713
Norm Quadratic Average: 12.78650188446045
Nearest Class Center Accuracy: 0.9115

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19889242947101593
Inter Cos: 0.14332182705402374
Norm Quadratic Average: 13.440021514892578
Nearest Class Center Accuracy: 0.944

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2773391604423523
Inter Cos: 0.11794356256723404
Norm Quadratic Average: 9.087471961975098
Nearest Class Center Accuracy: 0.97

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4570002555847168
Inter Cos: 0.12033580243587494
Norm Quadratic Average: 7.184278964996338
Nearest Class Center Accuracy: 0.979

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.806793212890625
Linear Weight Rank: 4031
Intra Cos: 0.7366494536399841
Inter Cos: 0.11993961781263351
Norm Quadratic Average: 67.07267761230469
Nearest Class Center Accuracy: 0.98

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.72426700592041
Linear Weight Rank: 3670
Intra Cos: 0.8378379940986633
Inter Cos: 0.14407822489738464
Norm Quadratic Average: 30.773681640625
Nearest Class Center Accuracy: 0.981

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5487462282180786
Linear Weight Rank: 10
Intra Cos: 0.863467276096344
Inter Cos: 0.19213023781776428
Norm Quadratic Average: 17.091596603393555
Nearest Class Center Accuracy: 0.9815

Output Layer:
Intra Cos: 0.8842355012893677
Inter Cos: 0.31569430232048035
Norm Quadratic Average: 9.227739334106445
Nearest Class Center Accuracy: 0.98

