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_0.005.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: 0.09880135208368301
Inter Cos: 0.10094815492630005
Norm Quadratic Average: 2.642632484436035
Nearest Class Center Accuracy: 0.8558666666666667

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17919015884399414
Inter Cos: 0.13511498272418976
Norm Quadratic Average: 1.4524664878845215
Nearest Class Center Accuracy: 0.9146666666666666

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22273409366607666
Inter Cos: 0.14991001784801483
Norm Quadratic Average: 0.9482198357582092
Nearest Class Center Accuracy: 0.9531333333333334

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3107413947582245
Inter Cos: 0.12445081770420074
Norm Quadratic Average: 0.5122351050376892
Nearest Class Center Accuracy: 0.9892833333333333

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.638714611530304
Inter Cos: 0.17601266503334045
Norm Quadratic Average: 0.40460020303726196
Nearest Class Center Accuracy: 0.9994666666666666

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8416862487792969
Inter Cos: 0.268418550491333
Norm Quadratic Average: 0.5954660177230835
Nearest Class Center Accuracy: 1.0

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9816282391548157
Inter Cos: 0.13825608789920807
Norm Quadratic Average: 0.9913662075996399
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.1335983276367188
Linear Weight Rank: 10
Intra Cos: 0.9971262812614441
Inter Cos: 0.2266678810119629
Norm Quadratic Average: 24.34987449645996
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.1354820728302
Linear Weight Rank: 1421
Intra Cos: 0.998030424118042
Inter Cos: 0.21302954852581024
Norm Quadratic Average: 17.093618392944336
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.135774850845337
Linear Weight Rank: 9
Intra Cos: 0.9982637166976929
Inter Cos: 0.18511155247688293
Norm Quadratic Average: 12.274741172790527
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9982458353042603
Inter Cos: 0.11160411685705185
Norm Quadratic Average: 9.304686546325684
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.015431202069669962
Accuracy: 0.996
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.034929532557725906, Weights: 0.007072391454130411
NC2 Equiangle: Features: 0.11621441311306424, Weights: 0.09132494396633573
NC3 Self-Duality: 0.03248055279254913
NC4 NCC Mismatch: 9.999999999998899e-05

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: 0.10897526890039444
Inter Cos: 0.10157202929258347
Norm Quadratic Average: 2.6270081996917725
Nearest Class Center Accuracy: 0.8691

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19029206037521362
Inter Cos: 0.13320358097553253
Norm Quadratic Average: 1.443793773651123
Nearest Class Center Accuracy: 0.924

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23672513663768768
Inter Cos: 0.14679677784442902
Norm Quadratic Average: 0.9447299838066101
Nearest Class Center Accuracy: 0.956

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3230757713317871
Inter Cos: 0.13552697002887726
Norm Quadratic Average: 0.5103120803833008
Nearest Class Center Accuracy: 0.9864

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6436591148376465
Inter Cos: 0.1911337822675705
Norm Quadratic Average: 0.4034229815006256
Nearest Class Center Accuracy: 0.9942

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8360251188278198
Inter Cos: 0.2768702805042267
Norm Quadratic Average: 0.5937411189079285
Nearest Class Center Accuracy: 0.9959

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9716604351997375
Inter Cos: 0.1496986448764801
Norm Quadratic Average: 0.9868674874305725
Nearest Class Center Accuracy: 0.9961

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.1335983276367188
Linear Weight Rank: 10
Intra Cos: 0.9809935688972473
Inter Cos: 0.2256903052330017
Norm Quadratic Average: 24.23148536682129
Nearest Class Center Accuracy: 0.9961

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.1354820728302
Linear Weight Rank: 1421
Intra Cos: 0.9814887046813965
Inter Cos: 0.21224036812782288
Norm Quadratic Average: 17.006221771240234
Nearest Class Center Accuracy: 0.9961

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.135774850845337
Linear Weight Rank: 9
Intra Cos: 0.9813369512557983
Inter Cos: 0.184976726770401
Norm Quadratic Average: 12.209054946899414
Nearest Class Center Accuracy: 0.9961

Output Layer:
Intra Cos: 0.9808635711669922
Inter Cos: 0.12550771236419678
Norm Quadratic Average: 9.251832008361816
Nearest Class Center Accuracy: 0.9961

