Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946067839860916
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: 0.10170476883649826
Inter Cos: 0.12443704158067703
Norm Quadratic Average: 74.33303833007812
Nearest Class Center Accuracy: 0.830625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1425752192735672
Inter Cos: 0.13031446933746338
Norm Quadratic Average: 49.63010025024414
Nearest Class Center Accuracy: 0.849125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14312505722045898
Inter Cos: 0.11476849764585495
Norm Quadratic Average: 50.33216094970703
Nearest Class Center Accuracy: 0.87225

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1685190200805664
Inter Cos: 0.09884542971849442
Norm Quadratic Average: 30.86251449584961
Nearest Class Center Accuracy: 0.907375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17869645357131958
Inter Cos: 0.0908978208899498
Norm Quadratic Average: 31.22083282470703
Nearest Class Center Accuracy: 0.934

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1955464631319046
Inter Cos: 0.09696689248085022
Norm Quadratic Average: 21.148273468017578
Nearest Class Center Accuracy: 0.975875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.29201528429985046
Inter Cos: 0.10161671042442322
Norm Quadratic Average: 16.383182525634766
Nearest Class Center Accuracy: 0.997125

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.78901672363281
Linear Weight Rank: 4031
Intra Cos: 0.5021518468856812
Inter Cos: 0.13521024584770203
Norm Quadratic Average: 106.58244323730469
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.498321533203125
Linear Weight Rank: 3671
Intra Cos: 0.6517459154129028
Inter Cos: 0.1637721061706543
Norm Quadratic Average: 54.383201599121094
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.056034803390503
Linear Weight Rank: 10
Intra Cos: 0.7812929153442383
Inter Cos: 0.18817129731178284
Norm Quadratic Average: 32.99039840698242
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9101733565330505
Inter Cos: 0.29342105984687805
Norm Quadratic Average: 17.106689453125
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.07848521387577057
Accuracy: 0.9755
NC1 Within Class Collapse: 1.6080446243286133
NC2 Equinorm: Features: 0.060776542872190475, Weights: 0.011287926696240902
NC2 Equiangle: Features: 0.20188645256890192, Weights: 0.08187139299180772
NC3 Self-Duality: 0.5783722996711731
NC4 NCC Mismatch: 0.007499999999999951

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
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: 0.1266023963689804
Inter Cos: 0.13434521853923798
Norm Quadratic Average: 73.50254821777344
Nearest Class Center Accuracy: 0.823

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1544996052980423
Inter Cos: 0.1586689054965973
Norm Quadratic Average: 49.4615478515625
Nearest Class Center Accuracy: 0.839

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14217254519462585
Inter Cos: 0.1432121843099594
Norm Quadratic Average: 50.180789947509766
Nearest Class Center Accuracy: 0.8575

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1571190059185028
Inter Cos: 0.1238599345088005
Norm Quadratic Average: 30.892919540405273
Nearest Class Center Accuracy: 0.908

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17022019624710083
Inter Cos: 0.11365737020969391
Norm Quadratic Average: 31.34156608581543
Nearest Class Center Accuracy: 0.9235

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19846050441265106
Inter Cos: 0.1012193113565445
Norm Quadratic Average: 21.22658920288086
Nearest Class Center Accuracy: 0.9505

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2772861123085022
Inter Cos: 0.1027965247631073
Norm Quadratic Average: 16.3372745513916
Nearest Class Center Accuracy: 0.9685

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.78901672363281
Linear Weight Rank: 4031
Intra Cos: 0.4429212510585785
Inter Cos: 0.13905197381973267
Norm Quadratic Average: 104.5503921508789
Nearest Class Center Accuracy: 0.975

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.498321533203125
Linear Weight Rank: 3671
Intra Cos: 0.5703186988830566
Inter Cos: 0.16850972175598145
Norm Quadratic Average: 53.00262451171875
Nearest Class Center Accuracy: 0.975

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.056034803390503
Linear Weight Rank: 10
Intra Cos: 0.6794476509094238
Inter Cos: 0.19786879420280457
Norm Quadratic Average: 32.03652572631836
Nearest Class Center Accuracy: 0.975

Output Layer:
Intra Cos: 0.802095890045166
Inter Cos: 0.27474987506866455
Norm Quadratic Average: 16.542139053344727
Nearest Class Center Accuracy: 0.9735

