Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_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: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0995020940899849
Inter Cos: 0.12094665318727493
Norm Quadratic Average: 84.05776977539062
Nearest Class Center Accuracy: 0.830125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14017897844314575
Inter Cos: 0.13043326139450073
Norm Quadratic Average: 54.978187561035156
Nearest Class Center Accuracy: 0.844375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13687770068645477
Inter Cos: 0.11950450390577316
Norm Quadratic Average: 53.48648452758789
Nearest Class Center Accuracy: 0.865625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1646004021167755
Inter Cos: 0.10246799886226654
Norm Quadratic Average: 33.031612396240234
Nearest Class Center Accuracy: 0.908125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1766285002231598
Inter Cos: 0.08133437484502792
Norm Quadratic Average: 34.40553665161133
Nearest Class Center Accuracy: 0.932125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19006367027759552
Inter Cos: 0.10188285261392593
Norm Quadratic Average: 23.58632469177246
Nearest Class Center Accuracy: 0.972625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2741260230541229
Inter Cos: 0.10458555072546005
Norm Quadratic Average: 18.323339462280273
Nearest Class Center Accuracy: 0.9965

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.63343811035156
Linear Weight Rank: 4031
Intra Cos: 0.4806487262248993
Inter Cos: 0.1383134126663208
Norm Quadratic Average: 115.42564392089844
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.06743240356445
Linear Weight Rank: 3671
Intra Cos: 0.6386245489120483
Inter Cos: 0.1795923262834549
Norm Quadratic Average: 61.46869659423828
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.207958936691284
Linear Weight Rank: 10
Intra Cos: 0.7649032473564148
Inter Cos: 0.20701956748962402
Norm Quadratic Average: 38.78064727783203
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9081851243972778
Inter Cos: 0.2581569254398346
Norm Quadratic Average: 20.90877342224121
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.10690848898887634
Accuracy: 0.973
NC1 Within Class Collapse: 1.6335428953170776
NC2 Equinorm: Features: 0.06286901235580444, Weights: 0.013226086273789406
NC2 Equiangle: Features: 0.2126254399617513, Weights: 0.08812508053249783
NC3 Self-Duality: 0.6310276389122009
NC4 NCC Mismatch: 0.007499999999999951

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133805871009827
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: 0.12482237070798874
Inter Cos: 0.13225385546684265
Norm Quadratic Average: 83.01329040527344
Nearest Class Center Accuracy: 0.8245

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15404559671878815
Inter Cos: 0.153485506772995
Norm Quadratic Average: 54.6037712097168
Nearest Class Center Accuracy: 0.8375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15522444248199463
Inter Cos: 0.1416974514722824
Norm Quadratic Average: 53.09231948852539
Nearest Class Center Accuracy: 0.8565

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17478573322296143
Inter Cos: 0.1153009906411171
Norm Quadratic Average: 32.915164947509766
Nearest Class Center Accuracy: 0.9015

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1799267828464508
Inter Cos: 0.10054159164428711
Norm Quadratic Average: 34.44296646118164
Nearest Class Center Accuracy: 0.926

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19443431496620178
Inter Cos: 0.1066221222281456
Norm Quadratic Average: 23.614933013916016
Nearest Class Center Accuracy: 0.95

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2664048671722412
Inter Cos: 0.11371205747127533
Norm Quadratic Average: 18.256000518798828
Nearest Class Center Accuracy: 0.9665

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.63343811035156
Linear Weight Rank: 4031
Intra Cos: 0.4132310450077057
Inter Cos: 0.15057694911956787
Norm Quadratic Average: 113.35924530029297
Nearest Class Center Accuracy: 0.9705

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.06743240356445
Linear Weight Rank: 3671
Intra Cos: 0.5343148708343506
Inter Cos: 0.19488105177879333
Norm Quadratic Average: 60.00624084472656
Nearest Class Center Accuracy: 0.971

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.207958936691284
Linear Weight Rank: 10
Intra Cos: 0.645007848739624
Inter Cos: 0.22965997457504272
Norm Quadratic Average: 37.69928741455078
Nearest Class Center Accuracy: 0.972

Output Layer:
Intra Cos: 0.7875361442565918
Inter Cos: 0.2895628809928894
Norm Quadratic Average: 20.21248435974121
Nearest Class Center Accuracy: 0.9685

