Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_weight_decay_0.0003.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: 0.11311887949705124
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: 0.10056465864181519
Inter Cos: 0.12336073070764542
Norm Quadratic Average: 86.15423583984375
Nearest Class Center Accuracy: 0.830875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14155058562755585
Inter Cos: 0.13734880089759827
Norm Quadratic Average: 57.2207145690918
Nearest Class Center Accuracy: 0.856375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13978657126426697
Inter Cos: 0.13065645098686218
Norm Quadratic Average: 56.51283264160156
Nearest Class Center Accuracy: 0.87

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1689767986536026
Inter Cos: 0.11084584891796112
Norm Quadratic Average: 34.50863265991211
Nearest Class Center Accuracy: 0.907875

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17393451929092407
Inter Cos: 0.10625962167978287
Norm Quadratic Average: 35.5484733581543
Nearest Class Center Accuracy: 0.932625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19167901575565338
Inter Cos: 0.10717194527387619
Norm Quadratic Average: 24.58266258239746
Nearest Class Center Accuracy: 0.973625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2816945016384125
Inter Cos: 0.08982483297586441
Norm Quadratic Average: 18.82630157470703
Nearest Class Center Accuracy: 0.995625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.93716430664062
Linear Weight Rank: 4031
Intra Cos: 0.4713774025440216
Inter Cos: 0.11551959812641144
Norm Quadratic Average: 118.54277801513672
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.399749755859375
Linear Weight Rank: 3670
Intra Cos: 0.6065633296966553
Inter Cos: 0.13709089159965515
Norm Quadratic Average: 64.23868560791016
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2728867530822754
Linear Weight Rank: 10
Intra Cos: 0.7330377697944641
Inter Cos: 0.16249796748161316
Norm Quadratic Average: 41.309486389160156
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9023898839950562
Inter Cos: 0.2611900269985199
Norm Quadratic Average: 22.40897560119629
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.10046475100517273
Accuracy: 0.976
NC1 Within Class Collapse: 1.6820436716079712
NC2 Equinorm: Features: 0.067475326359272, Weights: 0.011763744056224823
NC2 Equiangle: Features: 0.20310577816433376, Weights: 0.09373099009195963
NC3 Self-Duality: 0.6363774538040161
NC4 NCC Mismatch: 0.005499999999999949

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: 0.1266724318265915
Inter Cos: 0.13209585845470428
Norm Quadratic Average: 84.98106384277344
Nearest Class Center Accuracy: 0.8255

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15374250710010529
Inter Cos: 0.15741662681102753
Norm Quadratic Average: 56.690101623535156
Nearest Class Center Accuracy: 0.8495

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14642931520938873
Inter Cos: 0.14504632353782654
Norm Quadratic Average: 56.09275436401367
Nearest Class Center Accuracy: 0.865

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16006381809711456
Inter Cos: 0.1371389925479889
Norm Quadratic Average: 34.438682556152344
Nearest Class Center Accuracy: 0.8985

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1627286672592163
Inter Cos: 0.12912029027938843
Norm Quadratic Average: 35.57688903808594
Nearest Class Center Accuracy: 0.921

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19454900920391083
Inter Cos: 0.11290097236633301
Norm Quadratic Average: 24.54477310180664
Nearest Class Center Accuracy: 0.947

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2482677549123764
Inter Cos: 0.10960353910923004
Norm Quadratic Average: 18.7014102935791
Nearest Class Center Accuracy: 0.9695

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.93716430664062
Linear Weight Rank: 4031
Intra Cos: 0.40443891286849976
Inter Cos: 0.14185938239097595
Norm Quadratic Average: 116.05897521972656
Nearest Class Center Accuracy: 0.974

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.399749755859375
Linear Weight Rank: 3670
Intra Cos: 0.5251978635787964
Inter Cos: 0.15895169973373413
Norm Quadratic Average: 62.51166534423828
Nearest Class Center Accuracy: 0.9755

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2728867530822754
Linear Weight Rank: 10
Intra Cos: 0.6352758407592773
Inter Cos: 0.1679837703704834
Norm Quadratic Average: 40.010257720947266
Nearest Class Center Accuracy: 0.9765

Output Layer:
Intra Cos: 0.7857874631881714
Inter Cos: 0.27218756079673767
Norm Quadratic Average: 21.578428268432617
Nearest Class Center Accuracy: 0.9735

