Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_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: 0.08946067094802856
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: 0.1138247549533844
Inter Cos: 0.13752421736717224
Norm Quadratic Average: 43.77875900268555
Nearest Class Center Accuracy: 0.817875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15333203971385956
Inter Cos: 0.179932102560997
Norm Quadratic Average: 46.06210708618164
Nearest Class Center Accuracy: 0.792625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16613921523094177
Inter Cos: 0.1989159882068634
Norm Quadratic Average: 59.264373779296875
Nearest Class Center Accuracy: 0.80175

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1914139688014984
Inter Cos: 0.1973966360092163
Norm Quadratic Average: 37.48476028442383
Nearest Class Center Accuracy: 0.8355

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2186184674501419
Inter Cos: 0.21572794020175934
Norm Quadratic Average: 31.963335037231445
Nearest Class Center Accuracy: 0.876125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28487634658813477
Inter Cos: 0.21068406105041504
Norm Quadratic Average: 17.137605667114258
Nearest Class Center Accuracy: 0.9195

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4219041168689728
Inter Cos: 0.2560034692287445
Norm Quadratic Average: 11.879507064819336
Nearest Class Center Accuracy: 0.968

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.7706527709961
Linear Weight Rank: 4031
Intra Cos: 0.6336427927017212
Inter Cos: 0.2825939953327179
Norm Quadratic Average: 51.08880615234375
Nearest Class Center Accuracy: 0.995125

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.26161193847656
Linear Weight Rank: 3671
Intra Cos: 0.736934244632721
Inter Cos: 0.27220937609672546
Norm Quadratic Average: 33.28907012939453
Nearest Class Center Accuracy: 0.999

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2555441856384277
Linear Weight Rank: 10
Intra Cos: 0.7727142572402954
Inter Cos: 0.28423598408699036
Norm Quadratic Average: 25.92357063293457
Nearest Class Center Accuracy: 0.999375

Output Layer:
Intra Cos: 0.8075549006462097
Inter Cos: 0.3712342381477356
Norm Quadratic Average: 18.858551025390625
Nearest Class Center Accuracy: 0.99825

Test Set:
Average Loss: 0.06665631753206253
Accuracy: 0.9805
NC1 Within Class Collapse: 2.1303911209106445
NC2 Equinorm: Features: 0.11828917264938354, Weights: 0.02242225781083107
NC2 Equiangle: Features: 0.2669238620334201, Weights: 0.10198379092746311
NC3 Self-Duality: 0.4241751730442047
NC4 NCC Mismatch: 0.020000000000000018

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: 0.1349087953567505
Inter Cos: 0.1517208367586136
Norm Quadratic Average: 42.41465759277344
Nearest Class Center Accuracy: 0.8155

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16662441194057465
Inter Cos: 0.2070252150297165
Norm Quadratic Average: 44.60068130493164
Nearest Class Center Accuracy: 0.793

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18031978607177734
Inter Cos: 0.23773692548274994
Norm Quadratic Average: 57.352142333984375
Nearest Class Center Accuracy: 0.801

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16620613634586334
Inter Cos: 0.22920796275138855
Norm Quadratic Average: 36.489219665527344
Nearest Class Center Accuracy: 0.835

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1888657659292221
Inter Cos: 0.2493666410446167
Norm Quadratic Average: 31.20507049560547
Nearest Class Center Accuracy: 0.8695

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24586458504199982
Inter Cos: 0.22799693048000336
Norm Quadratic Average: 16.697134017944336
Nearest Class Center Accuracy: 0.917

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3629394769668579
Inter Cos: 0.2599954903125763
Norm Quadratic Average: 11.495762825012207
Nearest Class Center Accuracy: 0.9525

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.7706527709961
Linear Weight Rank: 4031
Intra Cos: 0.5538818836212158
Inter Cos: 0.2843616008758545
Norm Quadratic Average: 49.19010925292969
Nearest Class Center Accuracy: 0.9675

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.26161193847656
Linear Weight Rank: 3671
Intra Cos: 0.6498751640319824
Inter Cos: 0.2775633633136749
Norm Quadratic Average: 31.957040786743164
Nearest Class Center Accuracy: 0.974

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2555441856384277
Linear Weight Rank: 10
Intra Cos: 0.6828387975692749
Inter Cos: 0.3061690926551819
Norm Quadratic Average: 24.922855377197266
Nearest Class Center Accuracy: 0.9725

Output Layer:
Intra Cos: 0.7081933617591858
Inter Cos: 0.383888840675354
Norm Quadratic Average: 18.10193634033203
Nearest Class Center Accuracy: 0.9715

