Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_weight_decay_0.001.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946066349744797
Inter Cos: 0.11311887949705124
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: 0.10043518245220184
Inter Cos: 0.12445945292711258
Norm Quadratic Average: 79.76336669921875
Nearest Class Center Accuracy: 0.830625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13915807008743286
Inter Cos: 0.13455994427204132
Norm Quadratic Average: 53.6276741027832
Nearest Class Center Accuracy: 0.846625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14123159646987915
Inter Cos: 0.12289277464151382
Norm Quadratic Average: 54.9132080078125
Nearest Class Center Accuracy: 0.86725

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15713511407375336
Inter Cos: 0.10156932473182678
Norm Quadratic Average: 33.0761833190918
Nearest Class Center Accuracy: 0.899

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16234710812568665
Inter Cos: 0.08944921940565109
Norm Quadratic Average: 33.99563217163086
Nearest Class Center Accuracy: 0.926

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20311199128627777
Inter Cos: 0.08952885866165161
Norm Quadratic Average: 23.258790969848633
Nearest Class Center Accuracy: 0.969125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2792050242424011
Inter Cos: 0.0956851914525032
Norm Quadratic Average: 18.01131248474121
Nearest Class Center Accuracy: 0.99625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.61534881591797
Linear Weight Rank: 4031
Intra Cos: 0.4889611005783081
Inter Cos: 0.10904114693403244
Norm Quadratic Average: 114.41949462890625
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.05986404418945
Linear Weight Rank: 3670
Intra Cos: 0.6340393424034119
Inter Cos: 0.1305374801158905
Norm Quadratic Average: 60.52620315551758
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.216355323791504
Linear Weight Rank: 10
Intra Cos: 0.7578006982803345
Inter Cos: 0.1549106389284134
Norm Quadratic Average: 37.69185256958008
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.903609573841095
Inter Cos: 0.2232980728149414
Norm Quadratic Average: 19.851709365844727
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.0921883260011673
Accuracy: 0.978
NC1 Within Class Collapse: 1.7336461544036865
NC2 Equinorm: Features: 0.05357343330979347, Weights: 0.009016563184559345
NC2 Equiangle: Features: 0.19387215508355035, Weights: 0.08882264031304253
NC3 Self-Duality: 0.620492160320282
NC4 NCC Mismatch: 0.011499999999999955

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: 0.12331748753786087
Inter Cos: 0.12917813658714294
Norm Quadratic Average: 78.26325225830078
Nearest Class Center Accuracy: 0.823

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14303097128868103
Inter Cos: 0.14916974306106567
Norm Quadratic Average: 52.912784576416016
Nearest Class Center Accuracy: 0.841

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14312629401683807
Inter Cos: 0.14160120487213135
Norm Quadratic Average: 54.26324462890625
Nearest Class Center Accuracy: 0.86

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14988428354263306
Inter Cos: 0.11861446499824524
Norm Quadratic Average: 32.910118103027344
Nearest Class Center Accuracy: 0.891

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1530323624610901
Inter Cos: 0.10897117108106613
Norm Quadratic Average: 33.871273040771484
Nearest Class Center Accuracy: 0.914

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19147872924804688
Inter Cos: 0.09540660679340363
Norm Quadratic Average: 23.174903869628906
Nearest Class Center Accuracy: 0.9435

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.256194144487381
Inter Cos: 0.105476014316082
Norm Quadratic Average: 17.850696563720703
Nearest Class Center Accuracy: 0.9685

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.61534881591797
Linear Weight Rank: 4031
Intra Cos: 0.3964919447898865
Inter Cos: 0.11932821571826935
Norm Quadratic Average: 111.79609680175781
Nearest Class Center Accuracy: 0.976

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.05986404418945
Linear Weight Rank: 3670
Intra Cos: 0.5241767764091492
Inter Cos: 0.14537349343299866
Norm Quadratic Average: 58.75742721557617
Nearest Class Center Accuracy: 0.977

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.216355323791504
Linear Weight Rank: 10
Intra Cos: 0.6344313025474548
Inter Cos: 0.16173934936523438
Norm Quadratic Average: 36.412147521972656
Nearest Class Center Accuracy: 0.975

Output Layer:
Intra Cos: 0.7822129726409912
Inter Cos: 0.2468390315771103
Norm Quadratic Average: 19.037206649780273
Nearest Class Center Accuracy: 0.9755

