Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_weight_decay_0.02.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: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11949779093265533
Inter Cos: 0.1431732177734375
Norm Quadratic Average: 38.14565658569336
Nearest Class Center Accuracy: 0.809

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15504829585552216
Inter Cos: 0.1774294525384903
Norm Quadratic Average: 43.152015686035156
Nearest Class Center Accuracy: 0.78175

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17181135714054108
Inter Cos: 0.19900831580162048
Norm Quadratic Average: 56.017154693603516
Nearest Class Center Accuracy: 0.77825

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18384255468845367
Inter Cos: 0.1976945996284485
Norm Quadratic Average: 35.49269104003906
Nearest Class Center Accuracy: 0.80425

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22441984713077545
Inter Cos: 0.23772570490837097
Norm Quadratic Average: 25.342100143432617
Nearest Class Center Accuracy: 0.867375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3105968236923218
Inter Cos: 0.2918642461299896
Norm Quadratic Average: 13.49977970123291
Nearest Class Center Accuracy: 0.924875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.44429898262023926
Inter Cos: 0.3508324921131134
Norm Quadratic Average: 8.684117317199707
Nearest Class Center Accuracy: 0.96175

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.81843566894531
Linear Weight Rank: 4031
Intra Cos: 0.5881845951080322
Inter Cos: 0.3456847667694092
Norm Quadratic Average: 38.350624084472656
Nearest Class Center Accuracy: 0.979125

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.768235206604004
Linear Weight Rank: 3671
Intra Cos: 0.6536201238632202
Inter Cos: 0.3313748240470886
Norm Quadratic Average: 25.992036819458008
Nearest Class Center Accuracy: 0.983625

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9288502931594849
Linear Weight Rank: 10
Intra Cos: 0.6714545488357544
Inter Cos: 0.3137913644313812
Norm Quadratic Average: 19.242868423461914
Nearest Class Center Accuracy: 0.983875

Output Layer:
Intra Cos: 0.6941376328468323
Inter Cos: 0.420089453458786
Norm Quadratic Average: 14.750448226928711
Nearest Class Center Accuracy: 0.98275

Test Set:
Average Loss: 0.09998989284038544
Accuracy: 0.97
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.1773093193769455, Weights: 0.041673656553030014
NC2 Equiangle: Features: 0.29816360473632814, Weights: 0.16741157107883028
NC3 Self-Duality: 0.23202300071716309
NC4 NCC Mismatch: 0.023499999999999965

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: 0.1416417360305786
Inter Cos: 0.16512905061244965
Norm Quadratic Average: 37.075469970703125
Nearest Class Center Accuracy: 0.802

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16873234510421753
Inter Cos: 0.217494398355484
Norm Quadratic Average: 42.01153564453125
Nearest Class Center Accuracy: 0.78

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18279778957366943
Inter Cos: 0.24096788465976715
Norm Quadratic Average: 54.44161605834961
Nearest Class Center Accuracy: 0.776

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17015910148620605
Inter Cos: 0.23286941647529602
Norm Quadratic Average: 34.511531829833984
Nearest Class Center Accuracy: 0.8095

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2132195234298706
Inter Cos: 0.2605689465999603
Norm Quadratic Average: 24.70524024963379
Nearest Class Center Accuracy: 0.862

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2966112792491913
Inter Cos: 0.2809721827507019
Norm Quadratic Average: 13.125947952270508
Nearest Class Center Accuracy: 0.909

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.41192150115966797
Inter Cos: 0.32817307114601135
Norm Quadratic Average: 8.413569450378418
Nearest Class Center Accuracy: 0.942

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.81843566894531
Linear Weight Rank: 4031
Intra Cos: 0.5305604934692383
Inter Cos: 0.32076337933540344
Norm Quadratic Average: 37.124725341796875
Nearest Class Center Accuracy: 0.955

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.768235206604004
Linear Weight Rank: 3671
Intra Cos: 0.5826461911201477
Inter Cos: 0.31495657563209534
Norm Quadratic Average: 25.170846939086914
Nearest Class Center Accuracy: 0.96

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9288502931594849
Linear Weight Rank: 10
Intra Cos: 0.5922710299491882
Inter Cos: 0.329727441072464
Norm Quadratic Average: 18.65403938293457
Nearest Class Center Accuracy: 0.9605

Output Layer:
Intra Cos: 0.6007261276245117
Inter Cos: 0.43320685625076294
Norm Quadratic Average: 14.285503387451172
Nearest Class Center Accuracy: 0.9565

