Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.005.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.021450398489832878
Inter Cos: 0.11371058225631714
Norm Quadratic Average: 27.691619873046875
Nearest Class Center Accuracy: 0.279125

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023503920063376427
Inter Cos: 0.07623375952243805
Norm Quadratic Average: 69.90882873535156
Nearest Class Center Accuracy: 0.344125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.030678872019052505
Inter Cos: 0.08786998689174652
Norm Quadratic Average: 52.31283950805664
Nearest Class Center Accuracy: 0.37425

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02548546902835369
Inter Cos: 0.06577080488204956
Norm Quadratic Average: 54.447845458984375
Nearest Class Center Accuracy: 0.401625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.034718990325927734
Inter Cos: 0.08352626860141754
Norm Quadratic Average: 35.05615997314453
Nearest Class Center Accuracy: 0.427375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03344153240323067
Inter Cos: 0.0659196749329567
Norm Quadratic Average: 35.719154357910156
Nearest Class Center Accuracy: 0.468625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.046928513795137405
Inter Cos: 0.07781694829463959
Norm Quadratic Average: 22.736282348632812
Nearest Class Center Accuracy: 0.572875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06909279525279999
Inter Cos: 0.07863500714302063
Norm Quadratic Average: 16.00238800048828
Nearest Class Center Accuracy: 0.885125

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.76946258544922
Linear Weight Rank: 4031
Intra Cos: 0.21766074001789093
Inter Cos: 0.11162490397691727
Norm Quadratic Average: 88.52992248535156
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.253726959228516
Linear Weight Rank: 3671
Intra Cos: 0.4908550977706909
Inter Cos: 0.20605270564556122
Norm Quadratic Average: 42.834022521972656
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.133439540863037
Linear Weight Rank: 10
Intra Cos: 0.7166368365287781
Inter Cos: 0.30041325092315674
Norm Quadratic Average: 28.14007568359375
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8803064823150635
Inter Cos: 0.4715293347835541
Norm Quadratic Average: 17.889083862304688
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 1.8375616302490234
Accuracy: 0.5975
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.21819651126861572, Weights: 0.019046735018491745
NC2 Equiangle: Features: 0.43895907931857636, Weights: 0.0862220499250624
NC3 Self-Duality: 0.5822415351867676
NC4 NCC Mismatch: 0.13949999999999996

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018480457365512848
Inter Cos: 0.09352367371320724
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: 0.02331666089594364
Inter Cos: 0.0715116634964943
Norm Quadratic Average: 69.73583984375
Nearest Class Center Accuracy: 0.3615

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.030314641073346138
Inter Cos: 0.08556708693504333
Norm Quadratic Average: 52.1640739440918
Nearest Class Center Accuracy: 0.4035

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025091281160712242
Inter Cos: 0.06357397884130478
Norm Quadratic Average: 54.33580780029297
Nearest Class Center Accuracy: 0.4335

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.032373033463954926
Inter Cos: 0.08278129994869232
Norm Quadratic Average: 34.96495819091797
Nearest Class Center Accuracy: 0.4435

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02999849058687687
Inter Cos: 0.06458985060453415
Norm Quadratic Average: 35.602325439453125
Nearest Class Center Accuracy: 0.477

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03515731170773506
Inter Cos: 0.07683432847261429
Norm Quadratic Average: 22.623205184936523
Nearest Class Center Accuracy: 0.498

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.036810699850320816
Inter Cos: 0.0720696896314621
Norm Quadratic Average: 15.837403297424316
Nearest Class Center Accuracy: 0.581

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.76946258544922
Linear Weight Rank: 4031
Intra Cos: 0.06692368537187576
Inter Cos: 0.12009098380804062
Norm Quadratic Average: 84.772705078125
Nearest Class Center Accuracy: 0.616

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.253726959228516
Linear Weight Rank: 3671
Intra Cos: 0.13584202527999878
Inter Cos: 0.2380591183900833
Norm Quadratic Average: 39.0556526184082
Nearest Class Center Accuracy: 0.59

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.133439540863037
Linear Weight Rank: 10
Intra Cos: 0.19832369685173035
Inter Cos: 0.3532223105430603
Norm Quadratic Average: 24.811309814453125
Nearest Class Center Accuracy: 0.5805

Output Layer:
Intra Cos: 0.25879016518592834
Inter Cos: 0.48539257049560547
Norm Quadratic Average: 15.51679515838623
Nearest Class Center Accuracy: 0.5655

