Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_weight_decay_0.007.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946066349744797
Inter Cos: 0.11311888694763184
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: 0.10299798101186752
Inter Cos: 0.12432689964771271
Norm Quadratic Average: 66.24122619628906
Nearest Class Center Accuracy: 0.833375

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14805318415164948
Inter Cos: 0.1419459730386734
Norm Quadratic Average: 40.948760986328125
Nearest Class Center Accuracy: 0.850625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14856693148612976
Inter Cos: 0.1318567395210266
Norm Quadratic Average: 41.29246139526367
Nearest Class Center Accuracy: 0.868875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18109484016895294
Inter Cos: 0.12244568020105362
Norm Quadratic Average: 24.95935821533203
Nearest Class Center Accuracy: 0.91325

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1928296685218811
Inter Cos: 0.10741227865219116
Norm Quadratic Average: 26.00235939025879
Nearest Class Center Accuracy: 0.938875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23088006675243378
Inter Cos: 0.12180597335100174
Norm Quadratic Average: 17.866958618164062
Nearest Class Center Accuracy: 0.981375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.34528490900993347
Inter Cos: 0.12261281907558441
Norm Quadratic Average: 13.92589282989502
Nearest Class Center Accuracy: 0.998125

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.45707702636719
Linear Weight Rank: 4031
Intra Cos: 0.5906891822814941
Inter Cos: 0.13405661284923553
Norm Quadratic Average: 95.0577621459961
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.295446395874023
Linear Weight Rank: 3671
Intra Cos: 0.7571595907211304
Inter Cos: 0.17019599676132202
Norm Quadratic Average: 45.452449798583984
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8398810625076294
Linear Weight Rank: 10
Intra Cos: 0.8522526621818542
Inter Cos: 0.19139686226844788
Norm Quadratic Average: 26.469650268554688
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9229462146759033
Inter Cos: 0.22198204696178436
Norm Quadratic Average: 13.487730979919434
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.0742921735048294
Accuracy: 0.9765
NC1 Within Class Collapse: 1.4324662685394287
NC2 Equinorm: Features: 0.06082535907626152, Weights: 0.012980387546122074
NC2 Equiangle: Features: 0.20128790537516275, Weights: 0.07823700904846191
NC3 Self-Duality: 0.4604029357433319
NC4 NCC Mismatch: 0.005499999999999949

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: 0.12788498401641846
Inter Cos: 0.13402123749256134
Norm Quadratic Average: 65.49403381347656
Nearest Class Center Accuracy: 0.8265

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15766246616840363
Inter Cos: 0.16071473062038422
Norm Quadratic Average: 40.791160583496094
Nearest Class Center Accuracy: 0.8465

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.153395414352417
Inter Cos: 0.1441541463136673
Norm Quadratic Average: 41.0782585144043
Nearest Class Center Accuracy: 0.8625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17360162734985352
Inter Cos: 0.1267959177494049
Norm Quadratic Average: 24.895252227783203
Nearest Class Center Accuracy: 0.9075

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1834346354007721
Inter Cos: 0.11659908294677734
Norm Quadratic Average: 26.001665115356445
Nearest Class Center Accuracy: 0.9295

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2212793081998825
Inter Cos: 0.12046876549720764
Norm Quadratic Average: 17.83659553527832
Nearest Class Center Accuracy: 0.957

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3015495836734772
Inter Cos: 0.12453790754079819
Norm Quadratic Average: 13.820636749267578
Nearest Class Center Accuracy: 0.9715

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.45707702636719
Linear Weight Rank: 4031
Intra Cos: 0.504776120185852
Inter Cos: 0.14209841191768646
Norm Quadratic Average: 92.62904357910156
Nearest Class Center Accuracy: 0.976

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.295446395874023
Linear Weight Rank: 3671
Intra Cos: 0.6495248675346375
Inter Cos: 0.18048858642578125
Norm Quadratic Average: 43.985416412353516
Nearest Class Center Accuracy: 0.976

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8398810625076294
Linear Weight Rank: 10
Intra Cos: 0.7385575175285339
Inter Cos: 0.2054964154958725
Norm Quadratic Average: 25.550106048583984
Nearest Class Center Accuracy: 0.9755

Output Layer:
Intra Cos: 0.8111956119537354
Inter Cos: 0.24735720455646515
Norm Quadratic Average: 12.99620246887207
Nearest Class Center Accuracy: 0.974

