Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_weight_decay_0.0007.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: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11138904094696045
Inter Cos: 0.1290968507528305
Norm Quadratic Average: 45.39993667602539
Nearest Class Center Accuracy: 0.823125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15727359056472778
Inter Cos: 0.16351573169231415
Norm Quadratic Average: 42.58982467651367
Nearest Class Center Accuracy: 0.815625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1778261661529541
Inter Cos: 0.17886775732040405
Norm Quadratic Average: 54.91276550292969
Nearest Class Center Accuracy: 0.831375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19758659601211548
Inter Cos: 0.17935073375701904
Norm Quadratic Average: 36.530208587646484
Nearest Class Center Accuracy: 0.86575

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22338710725307465
Inter Cos: 0.19589178264141083
Norm Quadratic Average: 35.139854431152344
Nearest Class Center Accuracy: 0.909

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.29281720519065857
Inter Cos: 0.17434915900230408
Norm Quadratic Average: 21.28795623779297
Nearest Class Center Accuracy: 0.94875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4170514643192291
Inter Cos: 0.22305475175380707
Norm Quadratic Average: 16.679105758666992
Nearest Class Center Accuracy: 0.982375

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.03925323486328
Linear Weight Rank: 4031
Intra Cos: 0.6390469074249268
Inter Cos: 0.26979514956474304
Norm Quadratic Average: 74.47380065917969
Nearest Class Center Accuracy: 0.99825

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.63746643066406
Linear Weight Rank: 3671
Intra Cos: 0.7332540154457092
Inter Cos: 0.27115970849990845
Norm Quadratic Average: 48.30854797363281
Nearest Class Center Accuracy: 0.9995

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.468268632888794
Linear Weight Rank: 10
Intra Cos: 0.7729554772377014
Inter Cos: 0.261089563369751
Norm Quadratic Average: 37.55448913574219
Nearest Class Center Accuracy: 0.99975

Output Layer:
Intra Cos: 0.8051977157592773
Inter Cos: 0.32763540744781494
Norm Quadratic Average: 27.25288963317871
Nearest Class Center Accuracy: 0.999875

Test Set:
Average Loss: 0.0841174410879612
Accuracy: 0.9805
NC1 Within Class Collapse: 1.709702968597412
NC2 Equinorm: Features: 0.11352482438087463, Weights: 0.011946761049330235
NC2 Equiangle: Features: 0.25194850497775606, Weights: 0.09877794053819444
NC3 Self-Duality: 0.5431094765663147
NC4 NCC Mismatch: 0.009499999999999953

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133805871009827
Inter Cos: 0.11957792192697525
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: 0.1324065774679184
Inter Cos: 0.1458793431520462
Norm Quadratic Average: 44.540985107421875
Nearest Class Center Accuracy: 0.816

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17113690078258514
Inter Cos: 0.20013312995433807
Norm Quadratic Average: 41.84880065917969
Nearest Class Center Accuracy: 0.8175

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17779764533042908
Inter Cos: 0.21650883555412292
Norm Quadratic Average: 53.95979309082031
Nearest Class Center Accuracy: 0.826

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18004804849624634
Inter Cos: 0.21005035936832428
Norm Quadratic Average: 35.8823356628418
Nearest Class Center Accuracy: 0.8565

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.203898087143898
Inter Cos: 0.2260124683380127
Norm Quadratic Average: 34.59069061279297
Nearest Class Center Accuracy: 0.898

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2660149037837982
Inter Cos: 0.18768121302127838
Norm Quadratic Average: 20.898086547851562
Nearest Class Center Accuracy: 0.935

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.37128758430480957
Inter Cos: 0.21400345861911774
Norm Quadratic Average: 16.319869995117188
Nearest Class Center Accuracy: 0.9595

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.03925323486328
Linear Weight Rank: 4031
Intra Cos: 0.5739386081695557
Inter Cos: 0.24160417914390564
Norm Quadratic Average: 72.34522247314453
Nearest Class Center Accuracy: 0.971

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.63746643066406
Linear Weight Rank: 3671
Intra Cos: 0.6605914831161499
Inter Cos: 0.24470195174217224
Norm Quadratic Average: 46.827842712402344
Nearest Class Center Accuracy: 0.978

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.468268632888794
Linear Weight Rank: 10
Intra Cos: 0.6942548155784607
Inter Cos: 0.26368165016174316
Norm Quadratic Average: 36.4395637512207
Nearest Class Center Accuracy: 0.9785

Output Layer:
Intra Cos: 0.7150932550430298
Inter Cos: 0.3622598648071289
Norm Quadratic Average: 26.439678192138672
Nearest Class Center Accuracy: 0.976

