Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_weight_decay_0.001.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: 0.09948061406612396
Inter Cos: 0.12238585203886032
Norm Quadratic Average: 90.86347198486328
Nearest Class Center Accuracy: 0.83625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14342552423477173
Inter Cos: 0.13639385998249054
Norm Quadratic Average: 55.08769989013672
Nearest Class Center Accuracy: 0.857375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14163829386234283
Inter Cos: 0.1238621324300766
Norm Quadratic Average: 53.738136291503906
Nearest Class Center Accuracy: 0.874125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17294195294380188
Inter Cos: 0.10410255193710327
Norm Quadratic Average: 33.30649185180664
Nearest Class Center Accuracy: 0.909375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1778244525194168
Inter Cos: 0.08420616388320923
Norm Quadratic Average: 34.5810661315918
Nearest Class Center Accuracy: 0.931125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19507673382759094
Inter Cos: 0.10143690556287766
Norm Quadratic Average: 23.883121490478516
Nearest Class Center Accuracy: 0.9735

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2877347767353058
Inter Cos: 0.09436323493719101
Norm Quadratic Average: 18.166316986083984
Nearest Class Center Accuracy: 0.996

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.62920379638672
Linear Weight Rank: 4031
Intra Cos: 0.4926178455352783
Inter Cos: 0.11735589057207108
Norm Quadratic Average: 115.50565338134766
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.054203033447266
Linear Weight Rank: 3670
Intra Cos: 0.6374755501747131
Inter Cos: 0.15012162923812866
Norm Quadratic Average: 61.291290283203125
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2076425552368164
Linear Weight Rank: 10
Intra Cos: 0.7568913698196411
Inter Cos: 0.17072927951812744
Norm Quadratic Average: 38.26457977294922
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9054334163665771
Inter Cos: 0.2664582431316376
Norm Quadratic Average: 20.432729721069336
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.09187532450258731
Accuracy: 0.9745
NC1 Within Class Collapse: 1.683814525604248
NC2 Equinorm: Features: 0.06398429721593857, Weights: 0.010539041832089424
NC2 Equiangle: Features: 0.1988208770751953, Weights: 0.08884170320298937
NC3 Self-Duality: 0.622239887714386
NC4 NCC Mismatch: 0.00649999999999995

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: 0.1253151297569275
Inter Cos: 0.12786130607128143
Norm Quadratic Average: 89.6036376953125
Nearest Class Center Accuracy: 0.8305

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15690509974956512
Inter Cos: 0.14785103499889374
Norm Quadratic Average: 54.62973403930664
Nearest Class Center Accuracy: 0.844

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15509675443172455
Inter Cos: 0.12512022256851196
Norm Quadratic Average: 53.33169174194336
Nearest Class Center Accuracy: 0.866

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17655302584171295
Inter Cos: 0.10411302000284195
Norm Quadratic Average: 33.29194259643555
Nearest Class Center Accuracy: 0.8965

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1838613748550415
Inter Cos: 0.09333759546279907
Norm Quadratic Average: 34.63300704956055
Nearest Class Center Accuracy: 0.917

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19281154870986938
Inter Cos: 0.11557421833276749
Norm Quadratic Average: 23.897314071655273
Nearest Class Center Accuracy: 0.9445

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2640994191169739
Inter Cos: 0.09868966042995453
Norm Quadratic Average: 18.051015853881836
Nearest Class Center Accuracy: 0.9685

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.62920379638672
Linear Weight Rank: 4031
Intra Cos: 0.4163101017475128
Inter Cos: 0.12018535286188126
Norm Quadratic Average: 112.80475616455078
Nearest Class Center Accuracy: 0.973

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.054203033447266
Linear Weight Rank: 3670
Intra Cos: 0.5388106107711792
Inter Cos: 0.15793853998184204
Norm Quadratic Average: 59.44938659667969
Nearest Class Center Accuracy: 0.9755

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2076425552368164
Linear Weight Rank: 10
Intra Cos: 0.6414156556129456
Inter Cos: 0.18512395024299622
Norm Quadratic Average: 36.94148254394531
Nearest Class Center Accuracy: 0.9735

Output Layer:
Intra Cos: 0.7885426878929138
Inter Cos: 0.2980419397354126
Norm Quadratic Average: 19.60622787475586
Nearest Class Center Accuracy: 0.973

