Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.007.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: 0.11311887949705124
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: 0.10579852014780045
Inter Cos: 0.1261979192495346
Norm Quadratic Average: 64.92829132080078
Nearest Class Center Accuracy: 0.831375

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15864507853984833
Inter Cos: 0.14896415174007416
Norm Quadratic Average: 40.07546615600586
Nearest Class Center Accuracy: 0.8545

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15379630029201508
Inter Cos: 0.14276167750358582
Norm Quadratic Average: 40.543888092041016
Nearest Class Center Accuracy: 0.87

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17571891844272614
Inter Cos: 0.1238926351070404
Norm Quadratic Average: 25.065654754638672
Nearest Class Center Accuracy: 0.908375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18465587496757507
Inter Cos: 0.1119588240981102
Norm Quadratic Average: 26.363845825195312
Nearest Class Center Accuracy: 0.936125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2218349426984787
Inter Cos: 0.10669519752264023
Norm Quadratic Average: 17.81721305847168
Nearest Class Center Accuracy: 0.98025

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3294942378997803
Inter Cos: 0.12262308597564697
Norm Quadratic Average: 13.851016998291016
Nearest Class Center Accuracy: 0.998

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.4663314819336
Linear Weight Rank: 4031
Intra Cos: 0.5862175822257996
Inter Cos: 0.11438821256160736
Norm Quadratic Average: 94.64099884033203
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.29543113708496
Linear Weight Rank: 3671
Intra Cos: 0.7567525506019592
Inter Cos: 0.14449849724769592
Norm Quadratic Average: 45.398170471191406
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8294991254806519
Linear Weight Rank: 10
Intra Cos: 0.8595585823059082
Inter Cos: 0.1678473949432373
Norm Quadratic Average: 26.549297332763672
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9340262413024902
Inter Cos: 0.22355693578720093
Norm Quadratic Average: 13.57492446899414
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.07544792854785919
Accuracy: 0.978
NC1 Within Class Collapse: 1.4485912322998047
NC2 Equinorm: Features: 0.05515968054533005, Weights: 0.012853370048105717
NC2 Equiangle: Features: 0.19492354922824437, Weights: 0.08153129153781467
NC3 Self-Duality: 0.45634159445762634
NC4 NCC Mismatch: 0.0040000000000000036

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: 0.13222113251686096
Inter Cos: 0.13856953382492065
Norm Quadratic Average: 64.07830810546875
Nearest Class Center Accuracy: 0.827

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16253216564655304
Inter Cos: 0.17243888974189758
Norm Quadratic Average: 39.88392639160156
Nearest Class Center Accuracy: 0.853

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16005755960941315
Inter Cos: 0.1665305346250534
Norm Quadratic Average: 40.34303665161133
Nearest Class Center Accuracy: 0.8705

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16481637954711914
Inter Cos: 0.1479349583387375
Norm Quadratic Average: 25.06684112548828
Nearest Class Center Accuracy: 0.907

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.173008993268013
Inter Cos: 0.1355295330286026
Norm Quadratic Average: 26.392799377441406
Nearest Class Center Accuracy: 0.9265

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2073657363653183
Inter Cos: 0.10521742701530457
Norm Quadratic Average: 17.809865951538086
Nearest Class Center Accuracy: 0.955

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2979041635990143
Inter Cos: 0.12010958790779114
Norm Quadratic Average: 13.743881225585938
Nearest Class Center Accuracy: 0.9715

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.4663314819336
Linear Weight Rank: 4031
Intra Cos: 0.4995676875114441
Inter Cos: 0.14673613011837006
Norm Quadratic Average: 92.32645416259766
Nearest Class Center Accuracy: 0.977

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.29543113708496
Linear Weight Rank: 3671
Intra Cos: 0.6485483050346375
Inter Cos: 0.16136015951633453
Norm Quadratic Average: 44.00712585449219
Nearest Class Center Accuracy: 0.977

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8294991254806519
Linear Weight Rank: 10
Intra Cos: 0.7457395792007446
Inter Cos: 0.1844109296798706
Norm Quadratic Average: 25.64797019958496
Nearest Class Center Accuracy: 0.976

Output Layer:
Intra Cos: 0.8252297639846802
Inter Cos: 0.23546013236045837
Norm Quadratic Average: 13.07314682006836
Nearest Class Center Accuracy: 0.974

