Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.01.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: 23.532936096191406
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09810394048690796
Inter Cos: 0.11945892125368118
Norm Quadratic Average: 57.069549560546875
Nearest Class Center Accuracy: 0.835

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13655336201190948
Inter Cos: 0.13188354671001434
Norm Quadratic Average: 36.44877624511719
Nearest Class Center Accuracy: 0.852375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13958704471588135
Inter Cos: 0.12138521671295166
Norm Quadratic Average: 35.681365966796875
Nearest Class Center Accuracy: 0.87375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16995467245578766
Inter Cos: 0.10095576196908951
Norm Quadratic Average: 21.553394317626953
Nearest Class Center Accuracy: 0.91625

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19376657903194427
Inter Cos: 0.09398896247148514
Norm Quadratic Average: 21.984994888305664
Nearest Class Center Accuracy: 0.947

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22735489904880524
Inter Cos: 0.11032174527645111
Norm Quadratic Average: 15.023919105529785
Nearest Class Center Accuracy: 0.987625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.36567172408103943
Inter Cos: 0.10380382835865021
Norm Quadratic Average: 11.741364479064941
Nearest Class Center Accuracy: 0.99925

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.734378814697266
Linear Weight Rank: 4031
Intra Cos: 0.6518473625183105
Inter Cos: 0.11374703794717789
Norm Quadratic Average: 87.66033172607422
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.37053108215332
Linear Weight Rank: 3671
Intra Cos: 0.8193553686141968
Inter Cos: 0.13156814873218536
Norm Quadratic Average: 41.241981506347656
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7198176383972168
Linear Weight Rank: 10
Intra Cos: 0.8987237811088562
Inter Cos: 0.17010238766670227
Norm Quadratic Average: 23.767122268676758
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9419059753417969
Inter Cos: 0.25541824102401733
Norm Quadratic Average: 12.379931449890137
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.07484295868873596
Accuracy: 0.9765
NC1 Within Class Collapse: 1.3776004314422607
NC2 Equinorm: Features: 0.05975092947483063, Weights: 0.01443188264966011
NC2 Equiangle: Features: 0.20114337073432076, Weights: 0.08399014472961426
NC3 Self-Duality: 0.3739123046398163
NC4 NCC Mismatch: 0.0024999999999999467

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: 0.12144579738378525
Inter Cos: 0.12479784339666367
Norm Quadratic Average: 56.407413482666016
Nearest Class Center Accuracy: 0.826

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1506519317626953
Inter Cos: 0.15101198852062225
Norm Quadratic Average: 36.22598648071289
Nearest Class Center Accuracy: 0.8435

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15261024236679077
Inter Cos: 0.13785386085510254
Norm Quadratic Average: 35.417301177978516
Nearest Class Center Accuracy: 0.866

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1779053956270218
Inter Cos: 0.12648804485797882
Norm Quadratic Average: 21.491127014160156
Nearest Class Center Accuracy: 0.909

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19245274364948273
Inter Cos: 0.1107039600610733
Norm Quadratic Average: 21.973352432250977
Nearest Class Center Accuracy: 0.9365

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2281981110572815
Inter Cos: 0.11535131931304932
Norm Quadratic Average: 14.99231243133545
Nearest Class Center Accuracy: 0.9605

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3452598452568054
Inter Cos: 0.11481528729200363
Norm Quadratic Average: 11.647002220153809
Nearest Class Center Accuracy: 0.9725

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.734378814697266
Linear Weight Rank: 4031
Intra Cos: 0.5642474293708801
Inter Cos: 0.13922756910324097
Norm Quadratic Average: 85.42825317382812
Nearest Class Center Accuracy: 0.9745

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.37053108215332
Linear Weight Rank: 3671
Intra Cos: 0.7093075513839722
Inter Cos: 0.16286945343017578
Norm Quadratic Average: 39.94417190551758
Nearest Class Center Accuracy: 0.9755

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7198176383972168
Linear Weight Rank: 10
Intra Cos: 0.7850574851036072
Inter Cos: 0.16353076696395874
Norm Quadratic Average: 22.990522384643555
Nearest Class Center Accuracy: 0.976

Output Layer:
Intra Cos: 0.8366440534591675
Inter Cos: 0.23417578637599945
Norm Quadratic Average: 11.94282341003418
Nearest Class Center Accuracy: 0.976

