Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.0005.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.021450400352478027
Inter Cos: 0.11371058970689774
Norm Quadratic Average: 27.691617965698242
Nearest Class Center Accuracy: 0.279125

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02319418452680111
Inter Cos: 0.09993035346269608
Norm Quadratic Average: 86.69634246826172
Nearest Class Center Accuracy: 0.352625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02634291909635067
Inter Cos: 0.0929165855050087
Norm Quadratic Average: 64.55523681640625
Nearest Class Center Accuracy: 0.380375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023297274485230446
Inter Cos: 0.06627152860164642
Norm Quadratic Average: 68.41621398925781
Nearest Class Center Accuracy: 0.41075

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03184089809656143
Inter Cos: 0.07879094779491425
Norm Quadratic Average: 43.289154052734375
Nearest Class Center Accuracy: 0.4335

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0322013720870018
Inter Cos: 0.07109998166561127
Norm Quadratic Average: 44.25071334838867
Nearest Class Center Accuracy: 0.472625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0438651517033577
Inter Cos: 0.07544600963592529
Norm Quadratic Average: 28.10112190246582
Nearest Class Center Accuracy: 0.5565

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06444918364286423
Inter Cos: 0.07744068652391434
Norm Quadratic Average: 20.024574279785156
Nearest Class Center Accuracy: 0.83275

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.98066711425781
Linear Weight Rank: 4031
Intra Cos: 0.18414855003356934
Inter Cos: 0.10360938310623169
Norm Quadratic Average: 108.08747863769531
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.01516342163086
Linear Weight Rank: 3670
Intra Cos: 0.42216500639915466
Inter Cos: 0.18295828998088837
Norm Quadratic Average: 56.05924606323242
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4980545043945312
Linear Weight Rank: 10
Intra Cos: 0.6599916219711304
Inter Cos: 0.2785344123840332
Norm Quadratic Average: 38.98452377319336
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8652968406677246
Inter Cos: 0.4508994519710541
Norm Quadratic Average: 26.966407775878906
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 2.6725787200927735
Accuracy: 0.5825
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.22101379930973053, Weights: 0.017909632995724678
NC2 Equiangle: Features: 0.4231775919596354, Weights: 0.0890302234225803
NC3 Self-Duality: 0.635871171951294
NC4 NCC Mismatch: 0.14700000000000002

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018480457365512848
Inter Cos: 0.09352368116378784
Norm Quadratic Average: 27.530664443969727
Nearest Class Center Accuracy: 0.2895

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02261568233370781
Inter Cos: 0.0878220796585083
Norm Quadratic Average: 86.31330108642578
Nearest Class Center Accuracy: 0.3715

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025830069556832314
Inter Cos: 0.08214883506298065
Norm Quadratic Average: 64.20138549804688
Nearest Class Center Accuracy: 0.402

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02213825285434723
Inter Cos: 0.058276064693927765
Norm Quadratic Average: 68.16331481933594
Nearest Class Center Accuracy: 0.448

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.028048673644661903
Inter Cos: 0.06983926147222519
Norm Quadratic Average: 43.11931610107422
Nearest Class Center Accuracy: 0.461

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02814737893640995
Inter Cos: 0.06260480731725693
Norm Quadratic Average: 44.11237716674805
Nearest Class Center Accuracy: 0.4935

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.032396379858255386
Inter Cos: 0.06999946385622025
Norm Quadratic Average: 27.960723876953125
Nearest Class Center Accuracy: 0.502

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03532993048429489
Inter Cos: 0.07488629221916199
Norm Quadratic Average: 19.83169937133789
Nearest Class Center Accuracy: 0.575

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.98066711425781
Linear Weight Rank: 4031
Intra Cos: 0.059304896742105484
Inter Cos: 0.11144883930683136
Norm Quadratic Average: 104.18524932861328
Nearest Class Center Accuracy: 0.6295

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.01516342163086
Linear Weight Rank: 3670
Intra Cos: 0.1188042014837265
Inter Cos: 0.20855899155139923
Norm Quadratic Average: 51.6712760925293
Nearest Class Center Accuracy: 0.5915

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4980545043945312
Linear Weight Rank: 10
Intra Cos: 0.18567219376564026
Inter Cos: 0.3224707543849945
Norm Quadratic Average: 34.55723571777344
Nearest Class Center Accuracy: 0.5775

Output Layer:
Intra Cos: 0.271006315946579
Inter Cos: 0.49542438983917236
Norm Quadratic Average: 23.181602478027344
Nearest Class Center Accuracy: 0.552

