Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.0005.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: 0.11311887204647064
Norm Quadratic Average: 23.532939910888672
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11179579794406891
Inter Cos: 0.13469216227531433
Norm Quadratic Average: 47.56357192993164
Nearest Class Center Accuracy: 0.8225

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1537676900625229
Inter Cos: 0.17577430605888367
Norm Quadratic Average: 48.17133712768555
Nearest Class Center Accuracy: 0.80425

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16832801699638367
Inter Cos: 0.19389286637306213
Norm Quadratic Average: 64.2022476196289
Nearest Class Center Accuracy: 0.816625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19124598801136017
Inter Cos: 0.19117680191993713
Norm Quadratic Average: 43.05622482299805
Nearest Class Center Accuracy: 0.85425

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21795447170734406
Inter Cos: 0.1976633071899414
Norm Quadratic Average: 41.94075012207031
Nearest Class Center Accuracy: 0.89125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27361682057380676
Inter Cos: 0.18155966699123383
Norm Quadratic Average: 24.85814094543457
Nearest Class Center Accuracy: 0.92975

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.39682653546333313
Inter Cos: 0.20967774093151093
Norm Quadratic Average: 18.974397659301758
Nearest Class Center Accuracy: 0.972875

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.9876708984375
Linear Weight Rank: 4031
Intra Cos: 0.6043903827667236
Inter Cos: 0.23393169045448303
Norm Quadratic Average: 81.49796295166016
Nearest Class Center Accuracy: 0.99725

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.01515579223633
Linear Weight Rank: 3671
Intra Cos: 0.7168397307395935
Inter Cos: 0.23247677087783813
Norm Quadratic Average: 51.317134857177734
Nearest Class Center Accuracy: 0.999375

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.464613437652588
Linear Weight Rank: 10
Intra Cos: 0.7695757150650024
Inter Cos: 0.2649819254875183
Norm Quadratic Average: 39.09012985229492
Nearest Class Center Accuracy: 0.9995

Output Layer:
Intra Cos: 0.8218423128128052
Inter Cos: 0.38795605301856995
Norm Quadratic Average: 27.460041046142578
Nearest Class Center Accuracy: 0.999875

Test Set:
Average Loss: 0.08009186932444573
Accuracy: 0.981
NC1 Within Class Collapse: 1.7925450801849365
NC2 Equinorm: Features: 0.10483022034168243, Weights: 0.014219202101230621
NC2 Equiangle: Features: 0.2451748318142361, Weights: 0.09011103312174479
NC3 Self-Duality: 0.5484359264373779
NC4 NCC Mismatch: 0.01649999999999996

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957792937755585
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: 0.13273192942142487
Inter Cos: 0.14759652316570282
Norm Quadratic Average: 46.14765548706055
Nearest Class Center Accuracy: 0.8195

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16593845188617706
Inter Cos: 0.20030568540096283
Norm Quadratic Average: 46.72649002075195
Nearest Class Center Accuracy: 0.8035

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1763845980167389
Inter Cos: 0.22869379818439484
Norm Quadratic Average: 62.22198486328125
Nearest Class Center Accuracy: 0.824

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1642996072769165
Inter Cos: 0.21453964710235596
Norm Quadratic Average: 41.96510314941406
Nearest Class Center Accuracy: 0.8505

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18663479387760162
Inter Cos: 0.22591164708137512
Norm Quadratic Average: 40.9755744934082
Nearest Class Center Accuracy: 0.8795

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2336047738790512
Inter Cos: 0.20199108123779297
Norm Quadratic Average: 24.243988037109375
Nearest Class Center Accuracy: 0.9215

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.33844757080078125
Inter Cos: 0.22825433313846588
Norm Quadratic Average: 18.36201286315918
Nearest Class Center Accuracy: 0.95

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.9876708984375
Linear Weight Rank: 4031
Intra Cos: 0.5236267447471619
Inter Cos: 0.24335382878780365
Norm Quadratic Average: 78.4417495727539
Nearest Class Center Accuracy: 0.971

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.01515579223633
Linear Weight Rank: 3671
Intra Cos: 0.6293249726295471
Inter Cos: 0.24221210181713104
Norm Quadratic Average: 49.27155303955078
Nearest Class Center Accuracy: 0.976

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.464613437652588
Linear Weight Rank: 10
Intra Cos: 0.6786509156227112
Inter Cos: 0.2876455783843994
Norm Quadratic Average: 37.59077072143555
Nearest Class Center Accuracy: 0.976

Output Layer:
Intra Cos: 0.7226669788360596
Inter Cos: 0.39833343029022217
Norm Quadratic Average: 26.390348434448242
Nearest Class Center Accuracy: 0.974

