Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.0001.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: 23.532939910888672
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11172614246606827
Inter Cos: 0.13454008102416992
Norm Quadratic Average: 48.15037536621094
Nearest Class Center Accuracy: 0.82275

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15375402569770813
Inter Cos: 0.17540010809898376
Norm Quadratic Average: 49.05576705932617
Nearest Class Center Accuracy: 0.80425

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16839294135570526
Inter Cos: 0.19337143003940582
Norm Quadratic Average: 65.61587524414062
Nearest Class Center Accuracy: 0.818125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18993201851844788
Inter Cos: 0.18942752480506897
Norm Quadratic Average: 44.27588653564453
Nearest Class Center Accuracy: 0.855125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2168683260679245
Inter Cos: 0.1957477182149887
Norm Quadratic Average: 43.67585372924805
Nearest Class Center Accuracy: 0.8915

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2717081606388092
Inter Cos: 0.17794513702392578
Norm Quadratic Average: 26.151233673095703
Nearest Class Center Accuracy: 0.93075

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3937794268131256
Inter Cos: 0.21279622614383698
Norm Quadratic Average: 20.156795501708984
Nearest Class Center Accuracy: 0.974375

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.90472412109375
Linear Weight Rank: 4031
Intra Cos: 0.6030751466751099
Inter Cos: 0.23139958083629608
Norm Quadratic Average: 87.17438507080078
Nearest Class Center Accuracy: 0.99725

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.78920364379883
Linear Weight Rank: 3671
Intra Cos: 0.7140935659408569
Inter Cos: 0.2272234708070755
Norm Quadratic Average: 54.966495513916016
Nearest Class Center Accuracy: 0.99925

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4946494102478027
Linear Weight Rank: 10
Intra Cos: 0.7673987746238708
Inter Cos: 0.27163732051849365
Norm Quadratic Average: 41.942779541015625
Nearest Class Center Accuracy: 0.9995

Output Layer:
Intra Cos: 0.8226159811019897
Inter Cos: 0.3934229016304016
Norm Quadratic Average: 29.478179931640625
Nearest Class Center Accuracy: 0.999875

Test Set:
Average Loss: 0.08904202485084534
Accuracy: 0.979
NC1 Within Class Collapse: 1.773187279701233
NC2 Equinorm: Features: 0.10264462232589722, Weights: 0.01291968859732151
NC2 Equiangle: Features: 0.2432915793524848, Weights: 0.08978472815619574
NC3 Self-Duality: 0.5596013069152832
NC4 NCC Mismatch: 0.019499999999999962

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: 0.132609024643898
Inter Cos: 0.1474231779575348
Norm Quadratic Average: 46.72102355957031
Nearest Class Center Accuracy: 0.8195

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16617795825004578
Inter Cos: 0.20033040642738342
Norm Quadratic Average: 47.59006881713867
Nearest Class Center Accuracy: 0.805

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1763806939125061
Inter Cos: 0.22815462946891785
Norm Quadratic Average: 63.600303649902344
Nearest Class Center Accuracy: 0.825

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16420884430408478
Inter Cos: 0.21664674580097198
Norm Quadratic Average: 43.16730880737305
Nearest Class Center Accuracy: 0.851

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18649911880493164
Inter Cos: 0.2291392982006073
Norm Quadratic Average: 42.67276382446289
Nearest Class Center Accuracy: 0.881

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2343796044588089
Inter Cos: 0.20754173398017883
Norm Quadratic Average: 25.485557556152344
Nearest Class Center Accuracy: 0.9265

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3379821479320526
Inter Cos: 0.23754867911338806
Norm Quadratic Average: 19.504030227661133
Nearest Class Center Accuracy: 0.952

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.90472412109375
Linear Weight Rank: 4031
Intra Cos: 0.5242498517036438
Inter Cos: 0.23929260671138763
Norm Quadratic Average: 83.8958740234375
Nearest Class Center Accuracy: 0.971

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.78920364379883
Linear Weight Rank: 3671
Intra Cos: 0.6287136673927307
Inter Cos: 0.2511550188064575
Norm Quadratic Average: 52.76225280761719
Nearest Class Center Accuracy: 0.975

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4946494102478027
Linear Weight Rank: 10
Intra Cos: 0.6785927414894104
Inter Cos: 0.2955998480319977
Norm Quadratic Average: 40.32533645629883
Nearest Class Center Accuracy: 0.975

Output Layer:
Intra Cos: 0.726996660232544
Inter Cos: 0.40599822998046875
Norm Quadratic Average: 28.333293914794922
Nearest Class Center Accuracy: 0.973

