Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_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: 0.09116754680871964
Inter Cos: 0.10967153310775757
Norm Quadratic Average: 23.567678451538086
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1245889663696289
Inter Cos: 0.15767353773117065
Norm Quadratic Average: 34.5767936706543
Nearest Class Center Accuracy: 0.7991666666666667

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1533685177564621
Inter Cos: 0.19601349532604218
Norm Quadratic Average: 33.92321014404297
Nearest Class Center Accuracy: 0.7836166666666666

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19009292125701904
Inter Cos: 0.2384663075208664
Norm Quadratic Average: 40.63106155395508
Nearest Class Center Accuracy: 0.79695

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17301860451698303
Inter Cos: 0.2695188820362091
Norm Quadratic Average: 32.6595458984375
Nearest Class Center Accuracy: 0.8170666666666667

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2014571726322174
Inter Cos: 0.35101789236068726
Norm Quadratic Average: 26.048980712890625
Nearest Class Center Accuracy: 0.8655833333333334

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3307833671569824
Inter Cos: 0.4746853709220886
Norm Quadratic Average: 14.846846580505371
Nearest Class Center Accuracy: 0.9020333333333334

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.448421835899353
Inter Cos: 0.47499948740005493
Norm Quadratic Average: 13.153374671936035
Nearest Class Center Accuracy: 0.934

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.5580512285232544
Linear Weight Rank: 6
Intra Cos: 0.5689620971679688
Inter Cos: 0.4856061637401581
Norm Quadratic Average: 52.62908172607422
Nearest Class Center Accuracy: 0.9560333333333333

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.5593141317367554
Linear Weight Rank: 2714
Intra Cos: 0.638191282749176
Inter Cos: 0.47349923849105835
Norm Quadratic Average: 33.4811897277832
Nearest Class Center Accuracy: 0.9619333333333333

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5549888610839844
Linear Weight Rank: 9
Intra Cos: 0.6947411894798279
Inter Cos: 0.39250078797340393
Norm Quadratic Average: 20.29869270324707
Nearest Class Center Accuracy: 0.9638666666666666

Output Layer:
Intra Cos: 0.728998601436615
Inter Cos: 0.4201587736606598
Norm Quadratic Average: 13.512393951416016
Nearest Class Center Accuracy: 0.9647333333333333

Test Set:
Average Loss: 0.09052100293040276
Accuracy: 0.9741
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.15517960488796234, Weights: 0.04409632831811905
NC2 Equiangle: Features: 0.32643790774875214, Weights: 0.2219932132297092
NC3 Self-Duality: 0.12477979063987732
NC4 NCC Mismatch: 0.017199999999999993

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582915306091
Inter Cos: 0.12048852443695068
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13804057240486145
Inter Cos: 0.172727569937706
Norm Quadratic Average: 34.664546966552734
Nearest Class Center Accuracy: 0.8165

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17011626064777374
Inter Cos: 0.21582354605197906
Norm Quadratic Average: 33.94015884399414
Nearest Class Center Accuracy: 0.8006

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2069120854139328
Inter Cos: 0.2607409358024597
Norm Quadratic Average: 40.60786819458008
Nearest Class Center Accuracy: 0.8152

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18814432621002197
Inter Cos: 0.2682354748249054
Norm Quadratic Average: 32.636756896972656
Nearest Class Center Accuracy: 0.836

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21650028228759766
Inter Cos: 0.3721379339694977
Norm Quadratic Average: 26.100317001342773
Nearest Class Center Accuracy: 0.8806

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.34892067313194275
Inter Cos: 0.4955313205718994
Norm Quadratic Average: 14.925606727600098
Nearest Class Center Accuracy: 0.9122

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4575711190700531
Inter Cos: 0.4970889985561371
Norm Quadratic Average: 13.256118774414062
Nearest Class Center Accuracy: 0.9399

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 1.5580512285232544
Linear Weight Rank: 6
Intra Cos: 0.5652905106544495
Inter Cos: 0.5129629969596863
Norm Quadratic Average: 53.293663024902344
Nearest Class Center Accuracy: 0.9575

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 1.5593141317367554
Linear Weight Rank: 2714
Intra Cos: 0.6265738010406494
Inter Cos: 0.5003658533096313
Norm Quadratic Average: 34.018741607666016
Nearest Class Center Accuracy: 0.9638

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5549888610839844
Linear Weight Rank: 9
Intra Cos: 0.679433286190033
Inter Cos: 0.416745126247406
Norm Quadratic Average: 20.63418197631836
Nearest Class Center Accuracy: 0.9664

Output Layer:
Intra Cos: 0.7115504145622253
Inter Cos: 0.44158369302749634
Norm Quadratic Average: 13.744145393371582
Nearest Class Center Accuracy: 0.9669

