Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.0005.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01989092119038105
Inter Cos: 0.10477276146411896
Norm Quadratic Average: 27.59718132019043
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01842736080288887
Inter Cos: 0.07311619818210602
Norm Quadratic Average: 23.908124923706055
Nearest Class Center Accuracy: 0.4033

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02021208591759205
Inter Cos: 0.054320938885211945
Norm Quadratic Average: 11.793110847473145
Nearest Class Center Accuracy: 0.5332

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.015179510228335857
Inter Cos: 0.04330311343073845
Norm Quadratic Average: 10.296290397644043
Nearest Class Center Accuracy: 0.61244

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0204765684902668
Inter Cos: 0.036610815674066544
Norm Quadratic Average: 6.429811000823975
Nearest Class Center Accuracy: 0.7331

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03294385224580765
Inter Cos: 0.03763791173696518
Norm Quadratic Average: 6.495126724243164
Nearest Class Center Accuracy: 0.83438

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12357309460639954
Inter Cos: 0.09271752834320068
Norm Quadratic Average: 6.1483588218688965
Nearest Class Center Accuracy: 0.9531

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5448471307754517
Inter Cos: 0.11461982131004333
Norm Quadratic Average: 5.338964939117432
Nearest Class Center Accuracy: 0.99962

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 20.371965408325195
Linear Weight Rank: 4031
Intra Cos: 0.8540124297142029
Inter Cos: 0.0731581300497055
Norm Quadratic Average: 39.06186294555664
Nearest Class Center Accuracy: 0.99974

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 8.92956829071045
Linear Weight Rank: 3664
Intra Cos: 0.9601511359214783
Inter Cos: -0.003048255108296871
Norm Quadratic Average: 27.69985008239746
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.81589674949646
Linear Weight Rank: 10
Intra Cos: 0.9462149143218994
Inter Cos: 0.029358942061662674
Norm Quadratic Average: 18.738338470458984
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9910045266151428
Inter Cos: 0.2386290282011032
Norm Quadratic Average: 15.990727424621582
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.8382651615142822
Accuracy: 0.8422
NC1 Within Class Collapse: 4.247345924377441
NC2 Equinorm: Features: 0.1824120581150055, Weights: 0.024652112275362015
NC2 Equiangle: Features: 0.12589257558186848, Weights: 0.06069729063245985
NC3 Self-Duality: 0.22256767749786377
NC4 NCC Mismatch: 0.04520000000000002

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018526073545217514
Inter Cos: 0.1042705774307251
Norm Quadratic Average: 27.550134658813477
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017350338399410248
Inter Cos: 0.07476188987493515
Norm Quadratic Average: 23.889631271362305
Nearest Class Center Accuracy: 0.423

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.019009143114089966
Inter Cos: 0.05566270649433136
Norm Quadratic Average: 11.797703742980957
Nearest Class Center Accuracy: 0.5422

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.014100324362516403
Inter Cos: 0.04427279531955719
Norm Quadratic Average: 10.30999755859375
Nearest Class Center Accuracy: 0.615

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017495492473244667
Inter Cos: 0.03746119514107704
Norm Quadratic Average: 6.434323310852051
Nearest Class Center Accuracy: 0.6982

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025519752874970436
Inter Cos: 0.03942960873246193
Norm Quadratic Average: 6.475275993347168
Nearest Class Center Accuracy: 0.7487

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08424866944551468
Inter Cos: 0.0987042561173439
Norm Quadratic Average: 6.07952356338501
Nearest Class Center Accuracy: 0.7924

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.29407015442848206
Inter Cos: 0.19032981991767883
Norm Quadratic Average: 5.078377723693848
Nearest Class Center Accuracy: 0.8268

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 20.371965408325195
Linear Weight Rank: 4031
Intra Cos: 0.5215699672698975
Inter Cos: 0.253643661737442
Norm Quadratic Average: 35.96183395385742
Nearest Class Center Accuracy: 0.8148

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 8.92956829071045
Linear Weight Rank: 3664
Intra Cos: 0.5264168977737427
Inter Cos: 0.22610363364219666
Norm Quadratic Average: 24.707340240478516
Nearest Class Center Accuracy: 0.8303

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.81589674949646
Linear Weight Rank: 10
Intra Cos: 0.5267155170440674
Inter Cos: 0.25052255392074585
Norm Quadratic Average: 17.014286041259766
Nearest Class Center Accuracy: 0.8371

Output Layer:
Intra Cos: 0.5774420499801636
Inter Cos: 0.3393208980560303
Norm Quadratic Average: 14.29317569732666
Nearest Class Center Accuracy: 0.8415

