Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.005.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116754680871964
Inter Cos: 0.10967153310775757
Norm Quadratic Average: 23.567678451538086
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12310604751110077
Inter Cos: 0.1508389413356781
Norm Quadratic Average: 40.34722137451172
Nearest Class Center Accuracy: 0.8059

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17530669271945953
Inter Cos: 0.1789880245923996
Norm Quadratic Average: 41.22726058959961
Nearest Class Center Accuracy: 0.818

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20684269070625305
Inter Cos: 0.20618119835853577
Norm Quadratic Average: 41.38253402709961
Nearest Class Center Accuracy: 0.8621666666666666

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1864115446805954
Inter Cos: 0.22802865505218506
Norm Quadratic Average: 21.987565994262695
Nearest Class Center Accuracy: 0.90155

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2542994022369385
Inter Cos: 0.2784368097782135
Norm Quadratic Average: 13.3195219039917
Nearest Class Center Accuracy: 0.93545

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.47686874866485596
Inter Cos: 0.3082418143749237
Norm Quadratic Average: 7.123968601226807
Nearest Class Center Accuracy: 0.9727666666666667

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7208666801452637
Inter Cos: 0.4064066708087921
Norm Quadratic Average: 6.938407897949219
Nearest Class Center Accuracy: 0.9867833333333333

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.9884583950042725
Linear Weight Rank: 39
Intra Cos: 0.8046879172325134
Inter Cos: 0.4250308871269226
Norm Quadratic Average: 34.12594985961914
Nearest Class Center Accuracy: 0.9921166666666666

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.9907798767089844
Linear Weight Rank: 2734
Intra Cos: 0.8812992572784424
Inter Cos: 0.42543646693229675
Norm Quadratic Average: 27.15146255493164
Nearest Class Center Accuracy: 0.9954666666666667

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9840580224990845
Linear Weight Rank: 9
Intra Cos: 0.9069263935089111
Inter Cos: 0.39899972081184387
Norm Quadratic Average: 20.94024658203125
Nearest Class Center Accuracy: 0.9963833333333333

Output Layer:
Intra Cos: 0.9386579990386963
Inter Cos: 0.4613471031188965
Norm Quadratic Average: 18.341001510620117
Nearest Class Center Accuracy: 0.9966833333333334

Test Set:
Average Loss: 0.026991185208316892
Accuracy: 0.9908
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.10654881596565247, Weights: 0.04537978023290634
NC2 Equiangle: Features: 0.2703205108642578, Weights: 0.24824723137749566
NC3 Self-Duality: 0.056388914585113525
NC4 NCC Mismatch: 0.0044999999999999485

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582915306091
Inter Cos: 0.12048852443695068
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13664287328720093
Inter Cos: 0.16522444784641266
Norm Quadratic Average: 40.39837646484375
Nearest Class Center Accuracy: 0.8202

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1912260353565216
Inter Cos: 0.19215337932109833
Norm Quadratic Average: 41.16729736328125
Nearest Class Center Accuracy: 0.8339

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.220439612865448
Inter Cos: 0.2237483710050583
Norm Quadratic Average: 41.34532165527344
Nearest Class Center Accuracy: 0.8772

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1959237903356552
Inter Cos: 0.22421804070472717
Norm Quadratic Average: 21.944910049438477
Nearest Class Center Accuracy: 0.9158

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2624225914478302
Inter Cos: 0.2884069085121155
Norm Quadratic Average: 13.322749137878418
Nearest Class Center Accuracy: 0.9425

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.48933619260787964
Inter Cos: 0.3371197581291199
Norm Quadratic Average: 7.145788669586182
Nearest Class Center Accuracy: 0.9707

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7253625392913818
Inter Cos: 0.4307578504085541
Norm Quadratic Average: 6.984541893005371
Nearest Class Center Accuracy: 0.9827

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.9884583950042725
Linear Weight Rank: 39
Intra Cos: 0.8060042262077332
Inter Cos: 0.4475138485431671
Norm Quadratic Average: 34.42159652709961
Nearest Class Center Accuracy: 0.9871

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.9907798767089844
Linear Weight Rank: 2734
Intra Cos: 0.8774094581604004
Inter Cos: 0.4464743137359619
Norm Quadratic Average: 27.404308319091797
Nearest Class Center Accuracy: 0.9894

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9840580224990845
Linear Weight Rank: 9
Intra Cos: 0.9017317295074463
Inter Cos: 0.41864532232284546
Norm Quadratic Average: 21.128232955932617
Nearest Class Center Accuracy: 0.9892

Output Layer:
Intra Cos: 0.9285187125205994
Inter Cos: 0.4796449840068817
Norm Quadratic Average: 18.508882522583008
Nearest Class Center Accuracy: 0.9897

