Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.03.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946067839860916
Inter Cos: 0.11311887949705124
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: 0.10264218598604202
Inter Cos: 0.12432883679866791
Norm Quadratic Average: 19.449472427368164
Nearest Class Center Accuracy: 0.8325

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15140728652477264
Inter Cos: 0.14488430321216583
Norm Quadratic Average: 13.300982475280762
Nearest Class Center Accuracy: 0.85775

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15595197677612305
Inter Cos: 0.13700824975967407
Norm Quadratic Average: 13.592756271362305
Nearest Class Center Accuracy: 0.88

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21012794971466064
Inter Cos: 0.1257682889699936
Norm Quadratic Average: 8.112302780151367
Nearest Class Center Accuracy: 0.936875

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23891228437423706
Inter Cos: 0.13346797227859497
Norm Quadratic Average: 8.314665794372559
Nearest Class Center Accuracy: 0.97575

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.36361220479011536
Inter Cos: 0.12388353049755096
Norm Quadratic Average: 5.6829915046691895
Nearest Class Center Accuracy: 0.9985

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6979173421859741
Inter Cos: 0.14167755842208862
Norm Quadratic Average: 4.705694675445557
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 23.99799156188965
Linear Weight Rank: 4031
Intra Cos: 0.9441942572593689
Inter Cos: 0.11853466182947159
Norm Quadratic Average: 52.641117095947266
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.79214096069336
Linear Weight Rank: 3670
Intra Cos: 0.9821304678916931
Inter Cos: 0.17150861024856567
Norm Quadratic Average: 25.49856948852539
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5658272504806519
Linear Weight Rank: 10
Intra Cos: 0.9836345314979553
Inter Cos: 0.20522508025169373
Norm Quadratic Average: 14.485356330871582
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9854717254638672
Inter Cos: 0.29774653911590576
Norm Quadratic Average: 8.753819465637207
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.0702433500289917
Accuracy: 0.983
NC1 Within Class Collapse: 0.7348191738128662
NC2 Equinorm: Features: 0.07710334658622742, Weights: 0.01917063444852829
NC2 Equiangle: Features: 0.21351763407389324, Weights: 0.12305098639594184
NC3 Self-Duality: 0.0943194180727005
NC4 NCC Mismatch: 0.0030000000000000027

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: 0.1279267519712448
Inter Cos: 0.1342943161725998
Norm Quadratic Average: 19.1072940826416
Nearest Class Center Accuracy: 0.829

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15591678023338318
Inter Cos: 0.1604018658399582
Norm Quadratic Average: 13.150164604187012
Nearest Class Center Accuracy: 0.856

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16072317957878113
Inter Cos: 0.15893319249153137
Norm Quadratic Average: 13.464701652526855
Nearest Class Center Accuracy: 0.877

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20429131388664246
Inter Cos: 0.15055154263973236
Norm Quadratic Average: 8.066404342651367
Nearest Class Center Accuracy: 0.929

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24040921032428741
Inter Cos: 0.1532358080148697
Norm Quadratic Average: 8.285712242126465
Nearest Class Center Accuracy: 0.959

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.33397722244262695
Inter Cos: 0.13344809412956238
Norm Quadratic Average: 5.636086463928223
Nearest Class Center Accuracy: 0.978

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6177797913551331
Inter Cos: 0.1594735085964203
Norm Quadratic Average: 4.591627597808838
Nearest Class Center Accuracy: 0.984

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 23.99799156188965
Linear Weight Rank: 4031
Intra Cos: 0.8412815928459167
Inter Cos: 0.15862150490283966
Norm Quadratic Average: 50.30129623413086
Nearest Class Center Accuracy: 0.9835

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.79214096069336
Linear Weight Rank: 3670
Intra Cos: 0.8756061792373657
Inter Cos: 0.18331840634346008
Norm Quadratic Average: 24.368797302246094
Nearest Class Center Accuracy: 0.984

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5658272504806519
Linear Weight Rank: 10
Intra Cos: 0.8705916404724121
Inter Cos: 0.21336695551872253
Norm Quadratic Average: 13.89480972290039
Nearest Class Center Accuracy: 0.985

Output Layer:
Intra Cos: 0.8671278953552246
Inter Cos: 0.2979372441768646
Norm Quadratic Average: 8.39657974243164
Nearest Class Center Accuracy: 0.9845

