Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.02.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: 0.11967746913433075
Inter Cos: 0.14645186066627502
Norm Quadratic Average: 39.72162628173828
Nearest Class Center Accuracy: 0.809875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15148504078388214
Inter Cos: 0.18631094694137573
Norm Quadratic Average: 47.68187713623047
Nearest Class Center Accuracy: 0.768125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16228485107421875
Inter Cos: 0.20643071830272675
Norm Quadratic Average: 64.48365783691406
Nearest Class Center Accuracy: 0.766125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17889702320098877
Inter Cos: 0.21474222838878632
Norm Quadratic Average: 41.054962158203125
Nearest Class Center Accuracy: 0.803625

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20470944046974182
Inter Cos: 0.24957729876041412
Norm Quadratic Average: 29.359310150146484
Nearest Class Center Accuracy: 0.854125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2868640124797821
Inter Cos: 0.2848525941371918
Norm Quadratic Average: 15.0916748046875
Nearest Class Center Accuracy: 0.90225

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.42458590865135193
Inter Cos: 0.34294915199279785
Norm Quadratic Average: 9.318018913269043
Nearest Class Center Accuracy: 0.9485

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.8205680847168
Linear Weight Rank: 4031
Intra Cos: 0.5798599123954773
Inter Cos: 0.35548990964889526
Norm Quadratic Average: 39.78510665893555
Nearest Class Center Accuracy: 0.974875

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.768482208251953
Linear Weight Rank: 3670
Intra Cos: 0.6665307283401489
Inter Cos: 0.3275870084762573
Norm Quadratic Average: 26.44521713256836
Nearest Class Center Accuracy: 0.981125

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9390226602554321
Linear Weight Rank: 10
Intra Cos: 0.6975573301315308
Inter Cos: 0.32544684410095215
Norm Quadratic Average: 19.37737274169922
Nearest Class Center Accuracy: 0.981625

Output Layer:
Intra Cos: 0.7409477829933167
Inter Cos: 0.4122333526611328
Norm Quadratic Average: 14.581290245056152
Nearest Class Center Accuracy: 0.98225

Test Set:
Average Loss: 0.0930904986858368
Accuracy: 0.9705
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.15559716522693634, Weights: 0.037412989884614944
NC2 Equiangle: Features: 0.3003099229600694, Weights: 0.15612305535210502
NC3 Self-Duality: 0.2430119514465332
NC4 NCC Mismatch: 0.021499999999999964

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: 0.140702024102211
Inter Cos: 0.16486866772174835
Norm Quadratic Average: 38.334808349609375
Nearest Class Center Accuracy: 0.808

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1623671054840088
Inter Cos: 0.21844318509101868
Norm Quadratic Average: 46.031463623046875
Nearest Class Center Accuracy: 0.7765

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17742882668972015
Inter Cos: 0.2498769611120224
Norm Quadratic Average: 62.16545486450195
Nearest Class Center Accuracy: 0.768

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1579487919807434
Inter Cos: 0.24769428372383118
Norm Quadratic Average: 39.77791976928711
Nearest Class Center Accuracy: 0.8085

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18134598433971405
Inter Cos: 0.2797808051109314
Norm Quadratic Average: 28.552404403686523
Nearest Class Center Accuracy: 0.848

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25351473689079285
Inter Cos: 0.28286024928092957
Norm Quadratic Average: 14.616246223449707
Nearest Class Center Accuracy: 0.894

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3749178946018219
Inter Cos: 0.322045236825943
Norm Quadratic Average: 8.988762855529785
Nearest Class Center Accuracy: 0.9325

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.8205680847168
Linear Weight Rank: 4031
Intra Cos: 0.5130001306533813
Inter Cos: 0.33011651039123535
Norm Quadratic Average: 38.342384338378906
Nearest Class Center Accuracy: 0.9525

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.768482208251953
Linear Weight Rank: 3670
Intra Cos: 0.58919757604599
Inter Cos: 0.3256819248199463
Norm Quadratic Average: 25.46370506286621
Nearest Class Center Accuracy: 0.958

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9390226602554321
Linear Weight Rank: 10
Intra Cos: 0.6140637397766113
Inter Cos: 0.33391252160072327
Norm Quadratic Average: 18.671388626098633
Nearest Class Center Accuracy: 0.959

Output Layer:
Intra Cos: 0.6440560817718506
Inter Cos: 0.4161941409111023
Norm Quadratic Average: 14.01603889465332
Nearest Class Center Accuracy: 0.9605

