Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.001.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: 23.532934188842773
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11820615828037262
Inter Cos: 0.13754060864448547
Norm Quadratic Average: 47.07942581176758
Nearest Class Center Accuracy: 0.81725

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1635272055864334
Inter Cos: 0.16971290111541748
Norm Quadratic Average: 45.866207122802734
Nearest Class Center Accuracy: 0.80275

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17791776359081268
Inter Cos: 0.18318551778793335
Norm Quadratic Average: 59.685977935791016
Nearest Class Center Accuracy: 0.81525

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18783490359783173
Inter Cos: 0.1765444576740265
Norm Quadratic Average: 38.7301139831543
Nearest Class Center Accuracy: 0.85325

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21155576407909393
Inter Cos: 0.18854904174804688
Norm Quadratic Average: 36.765625
Nearest Class Center Accuracy: 0.894875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2891209125518799
Inter Cos: 0.17690415680408478
Norm Quadratic Average: 21.164045333862305
Nearest Class Center Accuracy: 0.93875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.41234007477760315
Inter Cos: 0.20240949094295502
Norm Quadratic Average: 16.47252082824707
Nearest Class Center Accuracy: 0.974875

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.63233184814453
Linear Weight Rank: 4031
Intra Cos: 0.6419626474380493
Inter Cos: 0.23444561660289764
Norm Quadratic Average: 72.21922302246094
Nearest Class Center Accuracy: 0.997875

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.0671501159668
Linear Weight Rank: 3671
Intra Cos: 0.7504172325134277
Inter Cos: 0.25304025411605835
Norm Quadratic Average: 46.80849075317383
Nearest Class Center Accuracy: 0.999875

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4533920288085938
Linear Weight Rank: 10
Intra Cos: 0.8008216619491577
Inter Cos: 0.2658943831920624
Norm Quadratic Average: 36.501224517822266
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8475982546806335
Inter Cos: 0.37347447872161865
Norm Quadratic Average: 26.259029388427734
Nearest Class Center Accuracy: 0.99975

Test Set:
Average Loss: 0.0773357423171401
Accuracy: 0.9805
NC1 Within Class Collapse: 1.7920680046081543
NC2 Equinorm: Features: 0.09134386479854584, Weights: 0.010779725387692451
NC2 Equiangle: Features: 0.24420909881591796, Weights: 0.09597722159491645
NC3 Self-Duality: 0.5221836566925049
NC4 NCC Mismatch: 0.01100000000000001

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133805871009827
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: 0.1331072747707367
Inter Cos: 0.1490510255098343
Norm Quadratic Average: 45.72846984863281
Nearest Class Center Accuracy: 0.811

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16759218275547028
Inter Cos: 0.19485826790332794
Norm Quadratic Average: 44.61513900756836
Nearest Class Center Accuracy: 0.798

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17437194287776947
Inter Cos: 0.2169339507818222
Norm Quadratic Average: 57.949256896972656
Nearest Class Center Accuracy: 0.812

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17000968754291534
Inter Cos: 0.20923225581645966
Norm Quadratic Average: 37.70998001098633
Nearest Class Center Accuracy: 0.845

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19046437740325928
Inter Cos: 0.22279417514801025
Norm Quadratic Average: 35.850982666015625
Nearest Class Center Accuracy: 0.882

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2558789551258087
Inter Cos: 0.20820219814777374
Norm Quadratic Average: 20.583881378173828
Nearest Class Center Accuracy: 0.933

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.36424940824508667
Inter Cos: 0.22594590485095978
Norm Quadratic Average: 15.92716121673584
Nearest Class Center Accuracy: 0.9565

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.63233184814453
Linear Weight Rank: 4031
Intra Cos: 0.5715485215187073
Inter Cos: 0.2599555552005768
Norm Quadratic Average: 69.28831481933594
Nearest Class Center Accuracy: 0.968

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.0671501159668
Linear Weight Rank: 3671
Intra Cos: 0.6791301965713501
Inter Cos: 0.2610221803188324
Norm Quadratic Average: 44.79655456542969
Nearest Class Center Accuracy: 0.9775

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4533920288085938
Linear Weight Rank: 10
Intra Cos: 0.7277163863182068
Inter Cos: 0.28267061710357666
Norm Quadratic Average: 34.92512130737305
Nearest Class Center Accuracy: 0.9775

Output Layer:
Intra Cos: 0.7702133655548096
Inter Cos: 0.3575599193572998
Norm Quadratic Average: 25.10102081298828
Nearest Class Center Accuracy: 0.976

