Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.007.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: 23.532939910888672
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11480358988046646
Inter Cos: 0.13900840282440186
Norm Quadratic Average: 42.930503845214844
Nearest Class Center Accuracy: 0.816875

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.153347447514534
Inter Cos: 0.18185488879680634
Norm Quadratic Average: 46.42718505859375
Nearest Class Center Accuracy: 0.78875

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16667035222053528
Inter Cos: 0.20191876590251923
Norm Quadratic Average: 59.712318420410156
Nearest Class Center Accuracy: 0.79775

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19017399847507477
Inter Cos: 0.20146898925304413
Norm Quadratic Average: 37.311763763427734
Nearest Class Center Accuracy: 0.833

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21816708147525787
Inter Cos: 0.22321493923664093
Norm Quadratic Average: 30.377464294433594
Nearest Class Center Accuracy: 0.874125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.29209983348846436
Inter Cos: 0.22039417922496796
Norm Quadratic Average: 15.797779083251953
Nearest Class Center Accuracy: 0.92075

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4346662759780884
Inter Cos: 0.2707403004169464
Norm Quadratic Average: 10.653827667236328
Nearest Class Center Accuracy: 0.967

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.47144317626953
Linear Weight Rank: 4031
Intra Cos: 0.6394941806793213
Inter Cos: 0.3033406138420105
Norm Quadratic Average: 46.07888412475586
Nearest Class Center Accuracy: 0.9935

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.318971633911133
Linear Weight Rank: 3671
Intra Cos: 0.7352374196052551
Inter Cos: 0.28988170623779297
Norm Quadratic Average: 30.367143630981445
Nearest Class Center Accuracy: 0.998375

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2034764289855957
Linear Weight Rank: 10
Intra Cos: 0.7654790282249451
Inter Cos: 0.29232800006866455
Norm Quadratic Average: 23.72730827331543
Nearest Class Center Accuracy: 0.99825

Output Layer:
Intra Cos: 0.7980563640594482
Inter Cos: 0.3727447986602783
Norm Quadratic Average: 17.552696228027344
Nearest Class Center Accuracy: 0.99675

Test Set:
Average Loss: 0.06807271206378937
Accuracy: 0.9785
NC1 Within Class Collapse: 2.3397216796875
NC2 Equinorm: Features: 0.12377119064331055, Weights: 0.026671597734093666
NC2 Equiangle: Features: 0.2717637379964193, Weights: 0.1070709334479438
NC3 Self-Duality: 0.37986519932746887
NC4 NCC Mismatch: 0.01649999999999996

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: 0.13595736026763916
Inter Cos: 0.15386271476745605
Norm Quadratic Average: 41.564186096191406
Nearest Class Center Accuracy: 0.815

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1665479838848114
Inter Cos: 0.20968157052993774
Norm Quadratic Average: 44.93022155761719
Nearest Class Center Accuracy: 0.789

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18083742260932922
Inter Cos: 0.2416626214981079
Norm Quadratic Average: 57.7581672668457
Nearest Class Center Accuracy: 0.7955

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1654423028230667
Inter Cos: 0.23514972627162933
Norm Quadratic Average: 36.31686782836914
Nearest Class Center Accuracy: 0.8325

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18877877295017242
Inter Cos: 0.2559763789176941
Norm Quadratic Average: 29.66275978088379
Nearest Class Center Accuracy: 0.8635

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2527300715446472
Inter Cos: 0.2375023514032364
Norm Quadratic Average: 15.385573387145996
Nearest Class Center Accuracy: 0.9135

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.37722688913345337
Inter Cos: 0.2646358013153076
Norm Quadratic Average: 10.30961799621582
Nearest Class Center Accuracy: 0.9525

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.47144317626953
Linear Weight Rank: 4031
Intra Cos: 0.5621073246002197
Inter Cos: 0.2879432141780853
Norm Quadratic Average: 44.39109802246094
Nearest Class Center Accuracy: 0.965

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.318971633911133
Linear Weight Rank: 3671
Intra Cos: 0.6511281132698059
Inter Cos: 0.2858923375606537
Norm Quadratic Average: 29.184511184692383
Nearest Class Center Accuracy: 0.9715

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2034764289855957
Linear Weight Rank: 10
Intra Cos: 0.6781859397888184
Inter Cos: 0.3049531579017639
Norm Quadratic Average: 22.83487319946289
Nearest Class Center Accuracy: 0.9705

Output Layer:
Intra Cos: 0.7016305327415466
Inter Cos: 0.3769267797470093
Norm Quadratic Average: 16.856786727905273
Nearest Class Center Accuracy: 0.9695

