Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg19_rand_seed_314159_test_samples_None_train_samples_None_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: 0.09116753935813904
Inter Cos: 0.10967151075601578
Norm Quadratic Average: 23.567678451538086
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06075271591544151
Inter Cos: 0.08182713389396667
Norm Quadratic Average: 2.4215009212493896
Nearest Class Center Accuracy: 0.80925

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10559762269258499
Inter Cos: 0.10091419517993927
Norm Quadratic Average: 1.3346635103225708
Nearest Class Center Accuracy: 0.8727333333333334

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10355541110038757
Inter Cos: 0.10005417466163635
Norm Quadratic Average: 1.049481749534607
Nearest Class Center Accuracy: 0.8784166666666666

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17482303082942963
Inter Cos: 0.11752841621637344
Norm Quadratic Average: 0.6424543261528015
Nearest Class Center Accuracy: 0.9369166666666666

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23162959516048431
Inter Cos: 0.12831144034862518
Norm Quadratic Average: 0.4645482897758484
Nearest Class Center Accuracy: 0.96285

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.31562340259552
Inter Cos: 0.14574655890464783
Norm Quadratic Average: 0.3936315178871155
Nearest Class Center Accuracy: 0.9733

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3513951599597931
Inter Cos: 0.14805768430233002
Norm Quadratic Average: 0.36101678013801575
Nearest Class Center Accuracy: 0.9748333333333333

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4263683557510376
Inter Cos: 0.1715952754020691
Norm Quadratic Average: 0.20719987154006958
Nearest Class Center Accuracy: 0.9918333333333333

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6701115965843201
Inter Cos: 0.2580701410770416
Norm Quadratic Average: 0.13432957231998444
Nearest Class Center Accuracy: 0.9982666666666666

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8108412623405457
Inter Cos: 0.2730921804904938
Norm Quadratic Average: 0.1220536082983017
Nearest Class Center Accuracy: 0.9990833333333333

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8607848882675171
Inter Cos: 0.19083251059055328
Norm Quadratic Average: 0.11297488957643509
Nearest Class Center Accuracy: 0.9999166666666667

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9110082983970642
Inter Cos: 0.13381755352020264
Norm Quadratic Average: 0.10386242717504501
Nearest Class Center Accuracy: 0.9999166666666667

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9880120158195496
Inter Cos: 0.1311001181602478
Norm Quadratic Average: 0.14966028928756714
Nearest Class Center Accuracy: 0.9999166666666667

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9971267580986023
Inter Cos: 0.16234171390533447
Norm Quadratic Average: 0.3966226577758789
Nearest Class Center Accuracy: 0.9999333333333333

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9986281394958496
Inter Cos: 0.2115931212902069
Norm Quadratic Average: 0.9874122738838196
Nearest Class Center Accuracy: 0.9999333333333333

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.034134864807129
Linear Weight Rank: 8
Intra Cos: 0.9989295601844788
Inter Cos: 0.2941715121269226
Norm Quadratic Average: 23.395505905151367
Nearest Class Center Accuracy: 0.9999333333333333

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0353846549987793
Linear Weight Rank: 1508
Intra Cos: 0.9989628195762634
Inter Cos: 0.2608443796634674
Norm Quadratic Average: 16.587793350219727
Nearest Class Center Accuracy: 0.9999333333333333

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0362424850463867
Linear Weight Rank: 9
Intra Cos: 0.9989607334136963
Inter Cos: 0.2029755562543869
Norm Quadratic Average: 12.059075355529785
Nearest Class Center Accuracy: 0.9999333333333333

Output Layer:
Intra Cos: 0.9990276098251343
Inter Cos: 0.23124319314956665
Norm Quadratic Average: 9.4221830368042
Nearest Class Center Accuracy: 0.9999333333333333

Test Set:
Average Loss: 0.02016109556667507
Accuracy: 0.9955
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.03582272306084633, Weights: 0.008744429796934128
NC2 Equiangle: Features: 0.17363508012559678, Weights: 0.1639866616990831
NC3 Self-Duality: 0.0353301502764225
NC4 NCC Mismatch: 0.00019999999999997797

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582915306091
Inter Cos: 0.12048851698637009
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06903325021266937
Inter Cos: 0.08466450870037079
Norm Quadratic Average: 2.4128894805908203
Nearest Class Center Accuracy: 0.8207

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11588316410779953
Inter Cos: 0.10287270694971085
Norm Quadratic Average: 1.3257800340652466
Nearest Class Center Accuracy: 0.8854

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11257653683423996
Inter Cos: 0.10253135859966278
Norm Quadratic Average: 1.0460931062698364
Nearest Class Center Accuracy: 0.8861

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18756352365016937
Inter Cos: 0.1278907209634781
Norm Quadratic Average: 0.6397810578346252
Nearest Class Center Accuracy: 0.9428

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2467290163040161
Inter Cos: 0.13627544045448303
Norm Quadratic Average: 0.4637579321861267
Nearest Class Center Accuracy: 0.9636

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3324543535709381
Inter Cos: 0.1590062528848648
Norm Quadratic Average: 0.39315763115882874
Nearest Class Center Accuracy: 0.9717

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.36704152822494507
Inter Cos: 0.16141963005065918
Norm Quadratic Average: 0.3601033389568329
Nearest Class Center Accuracy: 0.9744

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4367884397506714
Inter Cos: 0.18376325070858002
Norm Quadratic Average: 0.20681717991828918
Nearest Class Center Accuracy: 0.9884

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6773406267166138
Inter Cos: 0.26962292194366455
Norm Quadratic Average: 0.13437986373901367
Nearest Class Center Accuracy: 0.9922

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8046700954437256
Inter Cos: 0.2833680212497711
Norm Quadratic Average: 0.12219280004501343
Nearest Class Center Accuracy: 0.9938

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8605536818504333
Inter Cos: 0.20133960247039795
Norm Quadratic Average: 0.11283233761787415
Nearest Class Center Accuracy: 0.995

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9098386764526367
Inter Cos: 0.1430070847272873
Norm Quadratic Average: 0.1036207526922226
Nearest Class Center Accuracy: 0.9953

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9768826961517334
Inter Cos: 0.13406755030155182
Norm Quadratic Average: 0.14906294643878937
Nearest Class Center Accuracy: 0.9955

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9795756936073303
Inter Cos: 0.16629116237163544
Norm Quadratic Average: 0.3951360285282135
Nearest Class Center Accuracy: 0.9956

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9801079630851746
Inter Cos: 0.21445567905902863
Norm Quadratic Average: 0.9838777184486389
Nearest Class Center Accuracy: 0.9956

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.034134864807129
Linear Weight Rank: 8
Intra Cos: 0.9813247919082642
Inter Cos: 0.29488080739974976
Norm Quadratic Average: 23.310293197631836
Nearest Class Center Accuracy: 0.9956

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0353846549987793
Linear Weight Rank: 1508
Intra Cos: 0.9825800061225891
Inter Cos: 0.26205191016197205
Norm Quadratic Average: 16.52487564086914
Nearest Class Center Accuracy: 0.9957

Layer 18: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0362424850463867
Linear Weight Rank: 9
Intra Cos: 0.9834257364273071
Inter Cos: 0.20541790127754211
Norm Quadratic Average: 12.012097358703613
Nearest Class Center Accuracy: 0.9955

Output Layer:
Intra Cos: 0.9856204986572266
Inter Cos: 0.23168763518333435
Norm Quadratic Average: 9.384344100952148
Nearest Class Center Accuracy: 0.9954

