Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_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: 0.08946067094802856
Inter Cos: 0.11311887949705124
Norm Quadratic Average: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10425861924886703
Inter Cos: 0.12305423617362976
Norm Quadratic Average: 20.066333770751953
Nearest Class Center Accuracy: 0.832125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15738843381404877
Inter Cos: 0.14891788363456726
Norm Quadratic Average: 13.573050498962402
Nearest Class Center Accuracy: 0.861125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16610033810138702
Inter Cos: 0.14543353021144867
Norm Quadratic Average: 13.467494010925293
Nearest Class Center Accuracy: 0.882125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2191181480884552
Inter Cos: 0.13055822253227234
Norm Quadratic Average: 8.166580200195312
Nearest Class Center Accuracy: 0.940375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25513920187950134
Inter Cos: 0.13996008038520813
Norm Quadratic Average: 8.213329315185547
Nearest Class Center Accuracy: 0.973

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.381878525018692
Inter Cos: 0.13889583945274353
Norm Quadratic Average: 5.717586040496826
Nearest Class Center Accuracy: 0.997875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.698258101940155
Inter Cos: 0.17522937059402466
Norm Quadratic Average: 4.682170391082764
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 23.99551010131836
Linear Weight Rank: 4031
Intra Cos: 0.9466914534568787
Inter Cos: 0.1591944694519043
Norm Quadratic Average: 52.43262481689453
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.790508270263672
Linear Weight Rank: 3670
Intra Cos: 0.9817343354225159
Inter Cos: 0.1806216537952423
Norm Quadratic Average: 25.748249053955078
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5620304346084595
Linear Weight Rank: 10
Intra Cos: 0.9846736788749695
Inter Cos: 0.20806585252285004
Norm Quadratic Average: 14.782111167907715
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9879809021949768
Inter Cos: 0.315371036529541
Norm Quadratic Average: 9.052871704101562
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.06823852825164795
Accuracy: 0.9855
NC1 Within Class Collapse: 0.7424114346504211
NC2 Equinorm: Features: 0.08797456324100494, Weights: 0.027337567880749702
NC2 Equiangle: Features: 0.22618145412868923, Weights: 0.13864256540934244
NC3 Self-Duality: 0.09895101189613342
NC4 NCC Mismatch: 0.0014999999999999458

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
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: 0.12840549647808075
Inter Cos: 0.13654017448425293
Norm Quadratic Average: 19.808534622192383
Nearest Class Center Accuracy: 0.829

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16950483620166779
Inter Cos: 0.1699984073638916
Norm Quadratic Average: 13.476959228515625
Nearest Class Center Accuracy: 0.856

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17081153392791748
Inter Cos: 0.16742290556430817
Norm Quadratic Average: 13.367263793945312
Nearest Class Center Accuracy: 0.8815

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2099156230688095
Inter Cos: 0.15114855766296387
Norm Quadratic Average: 8.134808540344238
Nearest Class Center Accuracy: 0.927

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25138917565345764
Inter Cos: 0.1581864058971405
Norm Quadratic Average: 8.203812599182129
Nearest Class Center Accuracy: 0.953

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3591116666793823
Inter Cos: 0.1484355479478836
Norm Quadratic Average: 5.683126449584961
Nearest Class Center Accuracy: 0.979

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.610186755657196
Inter Cos: 0.18876896798610687
Norm Quadratic Average: 4.583086967468262
Nearest Class Center Accuracy: 0.983

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 23.99551010131836
Linear Weight Rank: 4031
Intra Cos: 0.8494542837142944
Inter Cos: 0.18976907432079315
Norm Quadratic Average: 50.30424880981445
Nearest Class Center Accuracy: 0.9845

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.790508270263672
Linear Weight Rank: 3670
Intra Cos: 0.8918842673301697
Inter Cos: 0.19588662683963776
Norm Quadratic Average: 24.673168182373047
Nearest Class Center Accuracy: 0.984

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5620304346084595
Linear Weight Rank: 10
Intra Cos: 0.8924737572669983
Inter Cos: 0.19869551062583923
Norm Quadratic Average: 14.19934368133545
Nearest Class Center Accuracy: 0.9845

Output Layer:
Intra Cos: 0.8986784815788269
Inter Cos: 0.29142215847969055
Norm Quadratic Average: 8.677356719970703
Nearest Class Center Accuracy: 0.9855

