Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.03.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: 23.532939910888672
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12164071947336197
Inter Cos: 0.14974252879619598
Norm Quadratic Average: 38.16116714477539
Nearest Class Center Accuracy: 0.804625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14944151043891907
Inter Cos: 0.18714040517807007
Norm Quadratic Average: 45.98822021484375
Nearest Class Center Accuracy: 0.76225

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15762630105018616
Inter Cos: 0.20637555420398712
Norm Quadratic Average: 63.781620025634766
Nearest Class Center Accuracy: 0.749625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16865795850753784
Inter Cos: 0.21370097994804382
Norm Quadratic Average: 42.31414031982422
Nearest Class Center Accuracy: 0.781

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19008931517601013
Inter Cos: 0.2578780949115753
Norm Quadratic Average: 31.288869857788086
Nearest Class Center Accuracy: 0.827125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26429301500320435
Inter Cos: 0.32429593801498413
Norm Quadratic Average: 17.437368392944336
Nearest Class Center Accuracy: 0.875375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.38450589776039124
Inter Cos: 0.36921876668930054
Norm Quadratic Average: 10.660700798034668
Nearest Class Center Accuracy: 0.927625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 24.014972686767578
Linear Weight Rank: 4031
Intra Cos: 0.5251631736755371
Inter Cos: 0.3577776551246643
Norm Quadratic Average: 42.79657745361328
Nearest Class Center Accuracy: 0.96125

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.83094310760498
Linear Weight Rank: 3670
Intra Cos: 0.6159628033638
Inter Cos: 0.3391273617744446
Norm Quadratic Average: 27.482952117919922
Nearest Class Center Accuracy: 0.969625

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7905555963516235
Linear Weight Rank: 10
Intra Cos: 0.6565548777580261
Inter Cos: 0.30402982234954834
Norm Quadratic Average: 18.736995697021484
Nearest Class Center Accuracy: 0.97275

Output Layer:
Intra Cos: 0.7075721621513367
Inter Cos: 0.3983801603317261
Norm Quadratic Average: 13.672120094299316
Nearest Class Center Accuracy: 0.97175

Test Set:
Average Loss: 0.12244323778152466
Accuracy: 0.963
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.17354422807693481, Weights: 0.040327221155166626
NC2 Equiangle: Features: 0.3177119361029731, Weights: 0.18922958374023438
NC3 Self-Duality: 0.19915072619915009
NC4 NCC Mismatch: 0.026499999999999968

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: 0.14248080551624298
Inter Cos: 0.16982559859752655
Norm Quadratic Average: 36.772438049316406
Nearest Class Center Accuracy: 0.8055

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15955111384391785
Inter Cos: 0.22055035829544067
Norm Quadratic Average: 44.34202575683594
Nearest Class Center Accuracy: 0.767

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.173095703125
Inter Cos: 0.24929171800613403
Norm Quadratic Average: 61.379703521728516
Nearest Class Center Accuracy: 0.7555

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15173004567623138
Inter Cos: 0.24559828639030457
Norm Quadratic Average: 40.89602279663086
Nearest Class Center Accuracy: 0.783

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17403951287269592
Inter Cos: 0.2860168516635895
Norm Quadratic Average: 30.34074592590332
Nearest Class Center Accuracy: 0.8275

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23975397646427155
Inter Cos: 0.3125157654285431
Norm Quadratic Average: 16.838207244873047
Nearest Class Center Accuracy: 0.8645

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3430468738079071
Inter Cos: 0.3480668067932129
Norm Quadratic Average: 10.242714881896973
Nearest Class Center Accuracy: 0.9165

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 24.014972686767578
Linear Weight Rank: 4031
Intra Cos: 0.46256664395332336
Inter Cos: 0.3394596576690674
Norm Quadratic Average: 41.094329833984375
Nearest Class Center Accuracy: 0.939

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.83094310760498
Linear Weight Rank: 3670
Intra Cos: 0.5381160974502563
Inter Cos: 0.32688674330711365
Norm Quadratic Average: 26.36994743347168
Nearest Class Center Accuracy: 0.9485

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7905555963516235
Linear Weight Rank: 10
Intra Cos: 0.5698328018188477
Inter Cos: 0.33368968963623047
Norm Quadratic Average: 17.99054718017578
Nearest Class Center Accuracy: 0.951

Output Layer:
Intra Cos: 0.6055684685707092
Inter Cos: 0.41308388113975525
Norm Quadratic Average: 13.09787654876709
Nearest Class Center Accuracy: 0.9525

