Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_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: 23.532941818237305
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09786196798086166
Inter Cos: 0.12021515518426895
Norm Quadratic Average: 54.9075813293457
Nearest Class Center Accuracy: 0.83325

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13897542655467987
Inter Cos: 0.1383259892463684
Norm Quadratic Average: 36.7387809753418
Nearest Class Center Accuracy: 0.850375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13999508321285248
Inter Cos: 0.12938198447227478
Norm Quadratic Average: 35.42494201660156
Nearest Class Center Accuracy: 0.872625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17443639039993286
Inter Cos: 0.10665645450353622
Norm Quadratic Average: 21.939584732055664
Nearest Class Center Accuracy: 0.91725

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18904250860214233
Inter Cos: 0.09154960513114929
Norm Quadratic Average: 22.317110061645508
Nearest Class Center Accuracy: 0.944125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23873600363731384
Inter Cos: 0.08729369938373566
Norm Quadratic Average: 15.321310997009277
Nearest Class Center Accuracy: 0.986

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3695903420448303
Inter Cos: 0.09782111644744873
Norm Quadratic Average: 11.945605278015137
Nearest Class Center Accuracy: 0.999125

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.7287712097168
Linear Weight Rank: 4031
Intra Cos: 0.646465003490448
Inter Cos: 0.11491245031356812
Norm Quadratic Average: 87.52632141113281
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.369123458862305
Linear Weight Rank: 3671
Intra Cos: 0.8100202679634094
Inter Cos: 0.1404280811548233
Norm Quadratic Average: 40.976871490478516
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7203614711761475
Linear Weight Rank: 10
Intra Cos: 0.8884185552597046
Inter Cos: 0.18749117851257324
Norm Quadratic Average: 23.68197250366211
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.932625412940979
Inter Cos: 0.26073604822158813
Norm Quadratic Average: 12.259196281433105
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.06958717119693757
Accuracy: 0.98
NC1 Within Class Collapse: 1.3465434312820435
NC2 Equinorm: Features: 0.07815872132778168, Weights: 0.01792955957353115
NC2 Equiangle: Features: 0.18662194146050348, Weights: 0.08294490708245171
NC3 Self-Duality: 0.3701901435852051
NC4 NCC Mismatch: 0.0050000000000000044

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
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: 0.12381970137357712
Inter Cos: 0.1291240006685257
Norm Quadratic Average: 54.220314025878906
Nearest Class Center Accuracy: 0.8265

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1587384045124054
Inter Cos: 0.15722806751728058
Norm Quadratic Average: 36.322303771972656
Nearest Class Center Accuracy: 0.846

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15222737193107605
Inter Cos: 0.13995707035064697
Norm Quadratic Average: 35.00910568237305
Nearest Class Center Accuracy: 0.8715

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1670546680688858
Inter Cos: 0.11842667311429977
Norm Quadratic Average: 21.799455642700195
Nearest Class Center Accuracy: 0.9135

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18161021173000336
Inter Cos: 0.1165136769413948
Norm Quadratic Average: 22.231285095214844
Nearest Class Center Accuracy: 0.9315

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22895313799381256
Inter Cos: 0.09509729593992233
Norm Quadratic Average: 15.24975872039795
Nearest Class Center Accuracy: 0.9655

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3349917531013489
Inter Cos: 0.10516342520713806
Norm Quadratic Average: 11.826200485229492
Nearest Class Center Accuracy: 0.976

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.7287712097168
Linear Weight Rank: 4031
Intra Cos: 0.5539361834526062
Inter Cos: 0.13070347905158997
Norm Quadratic Average: 85.09490966796875
Nearest Class Center Accuracy: 0.979

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.369123458862305
Linear Weight Rank: 3671
Intra Cos: 0.701604425907135
Inter Cos: 0.1526343822479248
Norm Quadratic Average: 39.550899505615234
Nearest Class Center Accuracy: 0.9785

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7203614711761475
Linear Weight Rank: 10
Intra Cos: 0.7765970230102539
Inter Cos: 0.1872464269399643
Norm Quadratic Average: 22.815582275390625
Nearest Class Center Accuracy: 0.9795

Output Layer:
Intra Cos: 0.8228082656860352
Inter Cos: 0.26590046286582947
Norm Quadratic Average: 11.776249885559082
Nearest Class Center Accuracy: 0.9805

