Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_weight_decay_0.0007.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: 23.532934188842773
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11161985248327255
Inter Cos: 0.13557368516921997
Norm Quadratic Average: 45.62847137451172
Nearest Class Center Accuracy: 0.81775

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14742639660835266
Inter Cos: 0.1690843552350998
Norm Quadratic Average: 46.266685485839844
Nearest Class Center Accuracy: 0.801375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16010896861553192
Inter Cos: 0.18601475656032562
Norm Quadratic Average: 61.4901237487793
Nearest Class Center Accuracy: 0.81075

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19477728009223938
Inter Cos: 0.18942414224147797
Norm Quadratic Average: 38.86825942993164
Nearest Class Center Accuracy: 0.84575

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2263249158859253
Inter Cos: 0.203016459941864
Norm Quadratic Average: 37.70413589477539
Nearest Class Center Accuracy: 0.884

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2764073312282562
Inter Cos: 0.1809263527393341
Norm Quadratic Average: 22.041255950927734
Nearest Class Center Accuracy: 0.9275

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.39573609828948975
Inter Cos: 0.20588086545467377
Norm Quadratic Average: 16.83424949645996
Nearest Class Center Accuracy: 0.973125

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.03355407714844
Linear Weight Rank: 4031
Intra Cos: 0.6189904808998108
Inter Cos: 0.22680538892745972
Norm Quadratic Average: 73.78724670410156
Nearest Class Center Accuracy: 0.997875

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.62895965576172
Linear Weight Rank: 3670
Intra Cos: 0.7261839509010315
Inter Cos: 0.2441006749868393
Norm Quadratic Average: 47.92127227783203
Nearest Class Center Accuracy: 0.999375

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.473834276199341
Linear Weight Rank: 10
Intra Cos: 0.7789415121078491
Inter Cos: 0.2683160901069641
Norm Quadratic Average: 37.597206115722656
Nearest Class Center Accuracy: 0.9995

Output Layer:
Intra Cos: 0.8225093483924866
Inter Cos: 0.39417117834091187
Norm Quadratic Average: 27.371244430541992
Nearest Class Center Accuracy: 0.99975

Test Set:
Average Loss: 0.0859746261537075
Accuracy: 0.9785
NC1 Within Class Collapse: 1.7750539779663086
NC2 Equinorm: Features: 0.12184806913137436, Weights: 0.013144497759640217
NC2 Equiangle: Features: 0.23943634033203126, Weights: 0.09524796803792318
NC3 Self-Duality: 0.5390739440917969
NC4 NCC Mismatch: 0.01200000000000001

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: 0.13510872423648834
Inter Cos: 0.15072891116142273
Norm Quadratic Average: 44.479286193847656
Nearest Class Center Accuracy: 0.813

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17098774015903473
Inter Cos: 0.19795486330986023
Norm Quadratic Average: 45.15620422363281
Nearest Class Center Accuracy: 0.796

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18140310049057007
Inter Cos: 0.222384512424469
Norm Quadratic Average: 59.923099517822266
Nearest Class Center Accuracy: 0.8115

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17323800921440125
Inter Cos: 0.2231663316488266
Norm Quadratic Average: 38.001075744628906
Nearest Class Center Accuracy: 0.846

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19468875229358673
Inter Cos: 0.23617640137672424
Norm Quadratic Average: 36.85041427612305
Nearest Class Center Accuracy: 0.877

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2421695441007614
Inter Cos: 0.20845070481300354
Norm Quadratic Average: 21.551599502563477
Nearest Class Center Accuracy: 0.9205

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3462069630622864
Inter Cos: 0.23981031775474548
Norm Quadratic Average: 16.404037475585938
Nearest Class Center Accuracy: 0.953

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.03355407714844
Linear Weight Rank: 4031
Intra Cos: 0.550528883934021
Inter Cos: 0.26766833662986755
Norm Quadratic Average: 71.58007049560547
Nearest Class Center Accuracy: 0.9725

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.62895965576172
Linear Weight Rank: 3670
Intra Cos: 0.646730899810791
Inter Cos: 0.2736532688140869
Norm Quadratic Average: 46.36885452270508
Nearest Class Center Accuracy: 0.974

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.473834276199341
Linear Weight Rank: 10
Intra Cos: 0.6922450065612793
Inter Cos: 0.30208438634872437
Norm Quadratic Average: 36.434242248535156
Nearest Class Center Accuracy: 0.9715

Output Layer:
Intra Cos: 0.7246692776679993
Inter Cos: 0.42204439640045166
Norm Quadratic Average: 26.50938606262207
Nearest Class Center Accuracy: 0.9695

