Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_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: 0.08946067094802856
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: 0.11603839695453644
Inter Cos: 0.1365669071674347
Norm Quadratic Average: 40.20938491821289
Nearest Class Center Accuracy: 0.816375

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15772688388824463
Inter Cos: 0.17270001769065857
Norm Quadratic Average: 42.06371307373047
Nearest Class Center Accuracy: 0.797875

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17768672108650208
Inter Cos: 0.1936863511800766
Norm Quadratic Average: 52.29967498779297
Nearest Class Center Accuracy: 0.804875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19654367864131927
Inter Cos: 0.19427712261676788
Norm Quadratic Average: 32.10999298095703
Nearest Class Center Accuracy: 0.832875

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23333914577960968
Inter Cos: 0.21766173839569092
Norm Quadratic Average: 24.55043601989746
Nearest Class Center Accuracy: 0.89075

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.32089963555336
Inter Cos: 0.2234226018190384
Norm Quadratic Average: 12.838772773742676
Nearest Class Center Accuracy: 0.940375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4676434099674225
Inter Cos: 0.2834073007106781
Norm Quadratic Average: 8.69443130493164
Nearest Class Center Accuracy: 0.975625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.750526428222656
Linear Weight Rank: 4031
Intra Cos: 0.6568635106086731
Inter Cos: 0.3073805868625641
Norm Quadratic Average: 39.461647033691406
Nearest Class Center Accuracy: 0.994125

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.404573440551758
Linear Weight Rank: 3671
Intra Cos: 0.7254542112350464
Inter Cos: 0.3049320876598358
Norm Quadratic Average: 27.1927490234375
Nearest Class Center Accuracy: 0.996625

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.140512228012085
Linear Weight Rank: 10
Intra Cos: 0.7407076954841614
Inter Cos: 0.29164814949035645
Norm Quadratic Average: 21.527761459350586
Nearest Class Center Accuracy: 0.9965

Output Layer:
Intra Cos: 0.7542988061904907
Inter Cos: 0.34368985891342163
Norm Quadratic Average: 16.65363883972168
Nearest Class Center Accuracy: 0.995

Test Set:
Average Loss: 0.07356846904754638
Accuracy: 0.977
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.14595216512680054, Weights: 0.029532045125961304
NC2 Equiangle: Features: 0.2771574232313368, Weights: 0.1312930213080512
NC3 Self-Duality: 0.3240526616573334
NC4 NCC Mismatch: 0.015499999999999958

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: 0.13780462741851807
Inter Cos: 0.1563042253255844
Norm Quadratic Average: 39.26362228393555
Nearest Class Center Accuracy: 0.809

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1725042760372162
Inter Cos: 0.21216800808906555
Norm Quadratic Average: 41.14221954345703
Nearest Class Center Accuracy: 0.7945

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18573515117168427
Inter Cos: 0.23446141183376312
Norm Quadratic Average: 51.09856414794922
Nearest Class Center Accuracy: 0.7985

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1788613498210907
Inter Cos: 0.2294931560754776
Norm Quadratic Average: 31.358686447143555
Nearest Class Center Accuracy: 0.8315

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21583396196365356
Inter Cos: 0.2521176338195801
Norm Quadratic Average: 24.04051399230957
Nearest Class Center Accuracy: 0.88

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2967405915260315
Inter Cos: 0.22507219016551971
Norm Quadratic Average: 12.54544734954834
Nearest Class Center Accuracy: 0.928

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4259165823459625
Inter Cos: 0.2750568985939026
Norm Quadratic Average: 8.469025611877441
Nearest Class Center Accuracy: 0.956

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.750526428222656
Linear Weight Rank: 4031
Intra Cos: 0.5937435030937195
Inter Cos: 0.29642802476882935
Norm Quadratic Average: 38.3093376159668
Nearest Class Center Accuracy: 0.9645

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.404573440551758
Linear Weight Rank: 3671
Intra Cos: 0.6524696350097656
Inter Cos: 0.288299024105072
Norm Quadratic Average: 26.38157081604004
Nearest Class Center Accuracy: 0.97

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.140512228012085
Linear Weight Rank: 10
Intra Cos: 0.6615936756134033
Inter Cos: 0.27994346618652344
Norm Quadratic Average: 20.90633201599121
Nearest Class Center Accuracy: 0.9695

Output Layer:
Intra Cos: 0.6635271310806274
Inter Cos: 0.3580198287963867
Norm Quadratic Average: 16.159791946411133
Nearest Class Center Accuracy: 0.97

