Model save path: ./New_Models/bn_False_dataset_CIFAR100_epochs_200_lr_0.01_model_type_vgg11_rand_seed_265358_test_samples_None_train_samples_None_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022893192246556282
Inter Cos: 0.07011394202709198
Norm Quadratic Average: 29.326324462890625
Nearest Class Center Accuracy: 0.03258

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03636198118329048
Inter Cos: 0.06441369652748108
Norm Quadratic Average: 30.730365753173828
Nearest Class Center Accuracy: 0.04406

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.033571530133485794
Inter Cos: 0.03141392767429352
Norm Quadratic Average: 20.392803192138672
Nearest Class Center Accuracy: 0.0555

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03242257982492447
Inter Cos: 0.027097314596176147
Norm Quadratic Average: 9.541426658630371
Nearest Class Center Accuracy: 0.06666

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.05674075335264206
Inter Cos: 0.04412943869829178
Norm Quadratic Average: 1.803802728652954
Nearest Class Center Accuracy: 0.07386

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.30427247285842896
Inter Cos: 0.29454106092453003
Norm Quadratic Average: 0.9852816462516785
Nearest Class Center Accuracy: 0.07964

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5685425996780396
Inter Cos: 0.5461124777793884
Norm Quadratic Average: 1.9502042531967163
Nearest Class Center Accuracy: 0.0843

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6725097298622131
Inter Cos: 0.6090183258056641
Norm Quadratic Average: 4.778048038482666
Nearest Class Center Accuracy: 0.09116

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.8005881309509277
Linear Weight Rank: 10
Intra Cos: 0.734640896320343
Inter Cos: 0.6354442238807678
Norm Quadratic Average: 54.24189758300781
Nearest Class Center Accuracy: 0.09414

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 3.9856579303741455
Linear Weight Rank: 2147
Intra Cos: 0.7890536189079285
Inter Cos: 0.6629309058189392
Norm Quadratic Average: 81.08490753173828
Nearest Class Center Accuracy: 0.0962

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 4.463803768157959
Linear Weight Rank: 97
Intra Cos: 0.8061447739601135
Inter Cos: 0.6530914306640625
Norm Quadratic Average: 85.7606430053711
Nearest Class Center Accuracy: 0.09744

Output Layer:
Intra Cos: 0.8884789943695068
Inter Cos: 0.7667244076728821
Norm Quadratic Average: 103.21907043457031
Nearest Class Center Accuracy: 0.09794

Test Set:
Average Loss: 5.965954814147949
Accuracy: 0.3007
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.34785324335098267, Weights: 0.06486896425485611
NC2 Equiangle: Features: 0.3525890250157828, Weights: 0.16716713028724747
NC3 Self-Duality: 0.6021403074264526
NC4 NCC Mismatch: 0.44630000000000003

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.006621266715228558
Inter Cos: 0.4067547917366028
Norm Quadratic Average: 29.42218589782715
Nearest Class Center Accuracy: 0.1136

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.014331397600471973
Inter Cos: 0.31686434149742126
Norm Quadratic Average: 30.916574478149414
Nearest Class Center Accuracy: 0.2167

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.019674628973007202
Inter Cos: 0.26306161284446716
Norm Quadratic Average: 20.531938552856445
Nearest Class Center Accuracy: 0.3134

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.021253395825624466
Inter Cos: 0.22670333087444305
Norm Quadratic Average: 9.583431243896484
Nearest Class Center Accuracy: 0.4318

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.030209548771381378
Inter Cos: 0.3572866916656494
Norm Quadratic Average: 1.8078749179840088
Nearest Class Center Accuracy: 0.4587

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.07191804051399231
Inter Cos: 0.794234573841095
Norm Quadratic Average: 0.9718933701515198
Nearest Class Center Accuracy: 0.3017

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.07175090909004211
Inter Cos: 0.8703441619873047
Norm Quadratic Average: 1.8869388103485107
Nearest Class Center Accuracy: 0.2527

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.07926567643880844
Inter Cos: 0.8481121063232422
Norm Quadratic Average: 4.551234722137451
Nearest Class Center Accuracy: 0.2794

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.8005881309509277
Linear Weight Rank: 10
Intra Cos: 0.07071399688720703
Inter Cos: 0.8296518325805664
Norm Quadratic Average: 51.071197509765625
Nearest Class Center Accuracy: 0.2916

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 3.9856579303741455
Linear Weight Rank: 2147
Intra Cos: 0.09592819213867188
Inter Cos: 0.8186969757080078
Norm Quadratic Average: 75.88916015625
Nearest Class Center Accuracy: 0.29

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 4.463803768157959
Linear Weight Rank: 97
Intra Cos: 0.20567047595977783
Inter Cos: 0.78245609998703
Norm Quadratic Average: 80.30559539794922
Nearest Class Center Accuracy: 0.2877

Output Layer:
Intra Cos: 0.15217460691928864
Inter Cos: 0.8081144690513611
Norm Quadratic Average: 95.39042663574219
Nearest Class Center Accuracy: 0.2795

