Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_weight_decay_0.01.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: 0.11584679782390594
Inter Cos: 0.1425762176513672
Norm Quadratic Average: 41.657291412353516
Nearest Class Center Accuracy: 0.812125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14888928830623627
Inter Cos: 0.1779392808675766
Norm Quadratic Average: 46.85844421386719
Nearest Class Center Accuracy: 0.784125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1611710637807846
Inter Cos: 0.19931717216968536
Norm Quadratic Average: 59.96188735961914
Nearest Class Center Accuracy: 0.7905

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19153375923633575
Inter Cos: 0.2104744166135788
Norm Quadratic Average: 35.33757781982422
Nearest Class Center Accuracy: 0.8235

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22730529308319092
Inter Cos: 0.23451992869377136
Norm Quadratic Average: 27.265666961669922
Nearest Class Center Accuracy: 0.86975

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.30164286494255066
Inter Cos: 0.23183587193489075
Norm Quadratic Average: 13.635854721069336
Nearest Class Center Accuracy: 0.92175

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4550131857395172
Inter Cos: 0.26856088638305664
Norm Quadratic Average: 8.896068572998047
Nearest Class Center Accuracy: 0.966625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.74721908569336
Linear Weight Rank: 4031
Intra Cos: 0.6528618335723877
Inter Cos: 0.300432950258255
Norm Quadratic Average: 39.58948516845703
Nearest Class Center Accuracy: 0.992

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.39990234375
Linear Weight Rank: 3670
Intra Cos: 0.7366285920143127
Inter Cos: 0.2885681092739105
Norm Quadratic Average: 27.201974868774414
Nearest Class Center Accuracy: 0.996375

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.152433395385742
Linear Weight Rank: 10
Intra Cos: 0.7607033252716064
Inter Cos: 0.2703723907470703
Norm Quadratic Average: 21.715770721435547
Nearest Class Center Accuracy: 0.99625

Output Layer:
Intra Cos: 0.7869541645050049
Inter Cos: 0.35518142580986023
Norm Quadratic Average: 16.79258155822754
Nearest Class Center Accuracy: 0.994125

Test Set:
Average Loss: 0.07726139020919799
Accuracy: 0.973
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.1383880376815796, Weights: 0.02651611529290676
NC2 Equiangle: Features: 0.27062464820014104, Weights: 0.12723859151204428
NC3 Self-Duality: 0.3264204263687134
NC4 NCC Mismatch: 0.017000000000000015

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: 0.13933894038200378
Inter Cos: 0.1599959135055542
Norm Quadratic Average: 40.42189025878906
Nearest Class Center Accuracy: 0.8065

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1682053804397583
Inter Cos: 0.20949770510196686
Norm Quadratic Average: 45.53304672241211
Nearest Class Center Accuracy: 0.781

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1816156655550003
Inter Cos: 0.23808029294013977
Norm Quadratic Average: 58.18938064575195
Nearest Class Center Accuracy: 0.7855

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17049835622310638
Inter Cos: 0.2456444501876831
Norm Quadratic Average: 34.404815673828125
Nearest Class Center Accuracy: 0.8225

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19699956476688385
Inter Cos: 0.27015021443367004
Norm Quadratic Average: 26.579782485961914
Nearest Class Center Accuracy: 0.8595

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2653220295906067
Inter Cos: 0.24872800707817078
Norm Quadratic Average: 13.264615058898926
Nearest Class Center Accuracy: 0.9195

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.40260905027389526
Inter Cos: 0.2983163595199585
Norm Quadratic Average: 8.639878273010254
Nearest Class Center Accuracy: 0.952

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 62.74721908569336
Linear Weight Rank: 4031
Intra Cos: 0.5814713835716248
Inter Cos: 0.33904293179512024
Norm Quadratic Average: 38.36992263793945
Nearest Class Center Accuracy: 0.965

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 25.39990234375
Linear Weight Rank: 3670
Intra Cos: 0.6549369692802429
Inter Cos: 0.3331614136695862
Norm Quadratic Average: 26.340503692626953
Nearest Class Center Accuracy: 0.97

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.152433395385742
Linear Weight Rank: 10
Intra Cos: 0.6726912260055542
Inter Cos: 0.31477364897727966
Norm Quadratic Average: 21.053190231323242
Nearest Class Center Accuracy: 0.968

Output Layer:
Intra Cos: 0.6889379620552063
Inter Cos: 0.3484589159488678
Norm Quadratic Average: 16.256574630737305
Nearest Class Center Accuracy: 0.968

