Model save path: ./New_Models/bn_True_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: 0.08946066349744797
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: 0.10485450178384781
Inter Cos: 0.12363018095493317
Norm Quadratic Average: 78.22261047363281
Nearest Class Center Accuracy: 0.8315

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1477586030960083
Inter Cos: 0.1386256366968155
Norm Quadratic Average: 55.836273193359375
Nearest Class Center Accuracy: 0.847625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14645522832870483
Inter Cos: 0.13622263073921204
Norm Quadratic Average: 55.6794548034668
Nearest Class Center Accuracy: 0.864625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1611482799053192
Inter Cos: 0.12607237696647644
Norm Quadratic Average: 33.47983932495117
Nearest Class Center Accuracy: 0.90225

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16777102649211884
Inter Cos: 0.11151279509067535
Norm Quadratic Average: 35.705970764160156
Nearest Class Center Accuracy: 0.925625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20024418830871582
Inter Cos: 0.0893154889345169
Norm Quadratic Average: 24.41516876220703
Nearest Class Center Accuracy: 0.969625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2742755115032196
Inter Cos: 0.09300079196691513
Norm Quadratic Average: 18.761938095092773
Nearest Class Center Accuracy: 0.995625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.97209930419922
Linear Weight Rank: 4031
Intra Cos: 0.46470949053764343
Inter Cos: 0.11282993108034134
Norm Quadratic Average: 116.10592651367188
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.006431579589844
Linear Weight Rank: 3671
Intra Cos: 0.6119972467422485
Inter Cos: 0.14524567127227783
Norm Quadratic Average: 62.454925537109375
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.266489267349243
Linear Weight Rank: 10
Intra Cos: 0.7417370676994324
Inter Cos: 0.1739244908094406
Norm Quadratic Average: 39.63894271850586
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8972107172012329
Inter Cos: 0.2504001557826996
Norm Quadratic Average: 21.042705535888672
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.1044444195330143
Accuracy: 0.9735
NC1 Within Class Collapse: 1.7389615774154663
NC2 Equinorm: Features: 0.06574934720993042, Weights: 0.008118304423987865
NC2 Equiangle: Features: 0.18556857638888888, Weights: 0.08650331497192383
NC3 Self-Duality: 0.6340383291244507
NC4 NCC Mismatch: 0.010000000000000009

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: 0.1247643306851387
Inter Cos: 0.13133935630321503
Norm Quadratic Average: 76.83929443359375
Nearest Class Center Accuracy: 0.824

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14701250195503235
Inter Cos: 0.1517452448606491
Norm Quadratic Average: 55.142662048339844
Nearest Class Center Accuracy: 0.8415

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1448814570903778
Inter Cos: 0.14417994022369385
Norm Quadratic Average: 55.017730712890625
Nearest Class Center Accuracy: 0.8615

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1496203988790512
Inter Cos: 0.120977021753788
Norm Quadratic Average: 33.32453918457031
Nearest Class Center Accuracy: 0.899

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15081281960010529
Inter Cos: 0.10809017717838287
Norm Quadratic Average: 35.550933837890625
Nearest Class Center Accuracy: 0.922

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17409192025661469
Inter Cos: 0.09429245442152023
Norm Quadratic Average: 24.2980899810791
Nearest Class Center Accuracy: 0.946

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22677959501743317
Inter Cos: 0.09624094516038895
Norm Quadratic Average: 18.56981086730957
Nearest Class Center Accuracy: 0.968

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.97209930419922
Linear Weight Rank: 4031
Intra Cos: 0.3748857080936432
Inter Cos: 0.11088094115257263
Norm Quadratic Average: 113.03650665283203
Nearest Class Center Accuracy: 0.9725

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.006431579589844
Linear Weight Rank: 3671
Intra Cos: 0.4937098026275635
Inter Cos: 0.14359034597873688
Norm Quadratic Average: 60.435035705566406
Nearest Class Center Accuracy: 0.9725

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.266489267349243
Linear Weight Rank: 10
Intra Cos: 0.6075523495674133
Inter Cos: 0.1815921664237976
Norm Quadratic Average: 38.20014190673828
Nearest Class Center Accuracy: 0.9705

Output Layer:
Intra Cos: 0.7649126648902893
Inter Cos: 0.29529398679733276
Norm Quadratic Average: 20.128963470458984
Nearest Class Center Accuracy: 0.971

