Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.0003.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: 0.09516660869121552
Inter Cos: 0.1033676266670227
Norm Quadratic Average: 25.565296173095703
Nearest Class Center Accuracy: 0.8499666666666666

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16091080009937286
Inter Cos: 0.12647400796413422
Norm Quadratic Average: 18.30026626586914
Nearest Class Center Accuracy: 0.9029166666666667

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1980196088552475
Inter Cos: 0.1364029198884964
Norm Quadratic Average: 18.760801315307617
Nearest Class Center Accuracy: 0.9336

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25736838579177856
Inter Cos: 0.1128825694322586
Norm Quadratic Average: 12.837108612060547
Nearest Class Center Accuracy: 0.98015

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.37271249294281006
Inter Cos: 0.11929868161678314
Norm Quadratic Average: 14.176424026489258
Nearest Class Center Accuracy: 0.9945

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.544593334197998
Inter Cos: 0.14308542013168335
Norm Quadratic Average: 11.372583389282227
Nearest Class Center Accuracy: 0.9997166666666667

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8319154381752014
Inter Cos: 0.10163583606481552
Norm Quadratic Average: 8.499682426452637
Nearest Class Center Accuracy: 0.9999833333333333

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 31.693370819091797
Linear Weight Rank: 4031
Intra Cos: 0.9490726590156555
Inter Cos: 0.01521578524261713
Norm Quadratic Average: 69.11292266845703
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 12.993898391723633
Linear Weight Rank: 3669
Intra Cos: 0.9811294674873352
Inter Cos: 0.008042005822062492
Norm Quadratic Average: 41.52157211303711
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.037489175796509
Linear Weight Rank: 10
Intra Cos: 0.9833986759185791
Inter Cos: 0.04702828824520111
Norm Quadratic Average: 24.54934310913086
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9969308972358704
Inter Cos: 0.15430393815040588
Norm Quadratic Average: 15.679722785949707
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.018888672294445494
Accuracy: 0.9949
NC1 Within Class Collapse: 0.2622992992401123
NC2 Equinorm: Features: 0.04672751948237419, Weights: 0.014069176279008389
NC2 Equiangle: Features: 0.07349426481458876, Weights: 0.05889675352308485
NC3 Self-Duality: 0.17059960961341858
NC4 NCC Mismatch: 0.0010000000000000009

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: 0.10554163157939911
Inter Cos: 0.1041375920176506
Norm Quadratic Average: 25.394989013671875
Nearest Class Center Accuracy: 0.8616

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17174863815307617
Inter Cos: 0.12483586370944977
Norm Quadratic Average: 18.17242431640625
Nearest Class Center Accuracy: 0.911

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21269407868385315
Inter Cos: 0.13400784134864807
Norm Quadratic Average: 18.658334732055664
Nearest Class Center Accuracy: 0.94

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27186673879623413
Inter Cos: 0.12369348108768463
Norm Quadratic Average: 12.79591178894043
Nearest Class Center Accuracy: 0.9793

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3868011236190796
Inter Cos: 0.12223830819129944
Norm Quadratic Average: 14.156482696533203
Nearest Class Center Accuracy: 0.99

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5498293042182922
Inter Cos: 0.14454884827136993
Norm Quadratic Average: 11.3831787109375
Nearest Class Center Accuracy: 0.993

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8272437453269958
Inter Cos: 0.10175329446792603
Norm Quadratic Average: 8.518177032470703
Nearest Class Center Accuracy: 0.9939

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 31.693370819091797
Linear Weight Rank: 4031
Intra Cos: 0.9341995716094971
Inter Cos: 0.013577324338257313
Norm Quadratic Average: 69.26025390625
Nearest Class Center Accuracy: 0.9942

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 12.993898391723633
Linear Weight Rank: 3669
Intra Cos: 0.9579842686653137
Inter Cos: 0.01868460699915886
Norm Quadratic Average: 41.59162902832031
Nearest Class Center Accuracy: 0.9947

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.037489175796509
Linear Weight Rank: 10
Intra Cos: 0.9559429287910461
Inter Cos: 0.05687091127038002
Norm Quadratic Average: 24.5947208404541
Nearest Class Center Accuracy: 0.9947

Output Layer:
Intra Cos: 0.9782203435897827
Inter Cos: 0.16245301067829132
Norm Quadratic Average: 15.697467803955078
Nearest Class Center Accuracy: 0.9948

