Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.02.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: 23.532934188842773
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12271779775619507
Inter Cos: 0.14827033877372742
Norm Quadratic Average: 39.88273239135742
Nearest Class Center Accuracy: 0.80825

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15750940144062042
Inter Cos: 0.18280832469463348
Norm Quadratic Average: 47.284461975097656
Nearest Class Center Accuracy: 0.77

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1690574586391449
Inter Cos: 0.1984502226114273
Norm Quadratic Average: 63.30876541137695
Nearest Class Center Accuracy: 0.758125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16833147406578064
Inter Cos: 0.20432773232460022
Norm Quadratic Average: 40.107723236083984
Nearest Class Center Accuracy: 0.790625

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20201238989830017
Inter Cos: 0.239501491189003
Norm Quadratic Average: 28.11290740966797
Nearest Class Center Accuracy: 0.855125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3066851794719696
Inter Cos: 0.25092920660972595
Norm Quadratic Average: 13.857312202453613
Nearest Class Center Accuracy: 0.911125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4579119086265564
Inter Cos: 0.3076516389846802
Norm Quadratic Average: 8.616287231445312
Nearest Class Center Accuracy: 0.953875

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.81661605834961
Linear Weight Rank: 4031
Intra Cos: 0.6117489337921143
Inter Cos: 0.32882171869277954
Norm Quadratic Average: 37.77769470214844
Nearest Class Center Accuracy: 0.97725

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.76812744140625
Linear Weight Rank: 3670
Intra Cos: 0.6882409453392029
Inter Cos: 0.3174577057361603
Norm Quadratic Average: 25.640697479248047
Nearest Class Center Accuracy: 0.982375

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9448895454406738
Linear Weight Rank: 10
Intra Cos: 0.7140817642211914
Inter Cos: 0.2988246977329254
Norm Quadratic Average: 19.124727249145508
Nearest Class Center Accuracy: 0.983375

Output Layer:
Intra Cos: 0.7490268349647522
Inter Cos: 0.33407777547836304
Norm Quadratic Average: 14.607158660888672
Nearest Class Center Accuracy: 0.983

Test Set:
Average Loss: 0.09513308143615723
Accuracy: 0.97
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.1415867805480957, Weights: 0.03416053205728531
NC2 Equiangle: Features: 0.29367603725857205, Weights: 0.16487053765190973
NC3 Self-Duality: 0.2225762903690338
NC4 NCC Mismatch: 0.02200000000000002

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133805871009827
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: 0.14060677587985992
Inter Cos: 0.1652003526687622
Norm Quadratic Average: 38.4984016418457
Nearest Class Center Accuracy: 0.8035

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16325433552265167
Inter Cos: 0.21383732557296753
Norm Quadratic Average: 45.6650390625
Nearest Class Center Accuracy: 0.771

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1740674525499344
Inter Cos: 0.24288812279701233
Norm Quadratic Average: 60.98603820800781
Nearest Class Center Accuracy: 0.7685

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1504727154970169
Inter Cos: 0.2435276061296463
Norm Quadratic Average: 38.735225677490234
Nearest Class Center Accuracy: 0.7985

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1827096790075302
Inter Cos: 0.27662092447280884
Norm Quadratic Average: 27.24366569519043
Nearest Class Center Accuracy: 0.8455

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27505025267601013
Inter Cos: 0.258259654045105
Norm Quadratic Average: 13.379495620727539
Nearest Class Center Accuracy: 0.909

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.40919241309165955
Inter Cos: 0.2950279116630554
Norm Quadratic Average: 8.287784576416016
Nearest Class Center Accuracy: 0.936

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.81661605834961
Linear Weight Rank: 4031
Intra Cos: 0.5466292500495911
Inter Cos: 0.32891204953193665
Norm Quadratic Average: 36.31873321533203
Nearest Class Center Accuracy: 0.955

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.76812744140625
Linear Weight Rank: 3670
Intra Cos: 0.6156136393547058
Inter Cos: 0.3253125548362732
Norm Quadratic Average: 24.64373016357422
Nearest Class Center Accuracy: 0.962

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9448895454406738
Linear Weight Rank: 10
Intra Cos: 0.6357806921005249
Inter Cos: 0.2990286946296692
Norm Quadratic Average: 18.374486923217773
Nearest Class Center Accuracy: 0.9605

Output Layer:
Intra Cos: 0.6599360704421997
Inter Cos: 0.3561341166496277
Norm Quadratic Average: 14.005138397216797
Nearest Class Center Accuracy: 0.96

