Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_weight_decay_0.02.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: 0.11311887949705124
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: 0.12112005054950714
Inter Cos: 0.14586779475212097
Norm Quadratic Average: 39.65871810913086
Nearest Class Center Accuracy: 0.8085

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15353511273860931
Inter Cos: 0.1820315569639206
Norm Quadratic Average: 46.61872482299805
Nearest Class Center Accuracy: 0.771125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16277693212032318
Inter Cos: 0.20082548260688782
Norm Quadratic Average: 62.8091926574707
Nearest Class Center Accuracy: 0.76025

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1763298362493515
Inter Cos: 0.21056361496448517
Norm Quadratic Average: 38.587738037109375
Nearest Class Center Accuracy: 0.799625

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20077408850193024
Inter Cos: 0.2611805200576782
Norm Quadratic Average: 27.538021087646484
Nearest Class Center Accuracy: 0.8585

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2947298288345337
Inter Cos: 0.26388978958129883
Norm Quadratic Average: 13.907174110412598
Nearest Class Center Accuracy: 0.912625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.44933637976646423
Inter Cos: 0.32224041223526
Norm Quadratic Average: 8.6474609375
Nearest Class Center Accuracy: 0.951625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.8178596496582
Linear Weight Rank: 4031
Intra Cos: 0.5983203053474426
Inter Cos: 0.3346598744392395
Norm Quadratic Average: 38.02193832397461
Nearest Class Center Accuracy: 0.97475

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.764460563659668
Linear Weight Rank: 3670
Intra Cos: 0.6782474517822266
Inter Cos: 0.3237581253051758
Norm Quadratic Average: 25.82193374633789
Nearest Class Center Accuracy: 0.982375

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9418796300888062
Linear Weight Rank: 10
Intra Cos: 0.705768346786499
Inter Cos: 0.2981582283973694
Norm Quadratic Average: 19.311630249023438
Nearest Class Center Accuracy: 0.983

Output Layer:
Intra Cos: 0.7442041635513306
Inter Cos: 0.3210611939430237
Norm Quadratic Average: 14.854222297668457
Nearest Class Center Accuracy: 0.983125

Test Set:
Average Loss: 0.09901299619674683
Accuracy: 0.9685
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.15865842998027802, Weights: 0.03906889632344246
NC2 Equiangle: Features: 0.3013891643948025, Weights: 0.16814068688286676
NC3 Self-Duality: 0.23379822075366974
NC4 NCC Mismatch: 0.027000000000000024

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133808106184006
Inter Cos: 0.11957792192697525
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: 0.14152246713638306
Inter Cos: 0.1663675159215927
Norm Quadratic Average: 38.34890365600586
Nearest Class Center Accuracy: 0.8055

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1671024113893509
Inter Cos: 0.21799373626708984
Norm Quadratic Average: 45.09644317626953
Nearest Class Center Accuracy: 0.7755

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18060830235481262
Inter Cos: 0.2466256320476532
Norm Quadratic Average: 60.64187240600586
Nearest Class Center Accuracy: 0.7685

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15674345195293427
Inter Cos: 0.24860607087612152
Norm Quadratic Average: 37.379722595214844
Nearest Class Center Accuracy: 0.8085

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18070611357688904
Inter Cos: 0.29386481642723083
Norm Quadratic Average: 26.75193214416504
Nearest Class Center Accuracy: 0.854

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26600828766822815
Inter Cos: 0.2624092102050781
Norm Quadratic Average: 13.458248138427734
Nearest Class Center Accuracy: 0.898

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.40324681997299194
Inter Cos: 0.30622509121894836
Norm Quadratic Average: 8.33465576171875
Nearest Class Center Accuracy: 0.9305

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 38.8178596496582
Linear Weight Rank: 4031
Intra Cos: 0.5341680645942688
Inter Cos: 0.31597900390625
Norm Quadratic Average: 36.607154846191406
Nearest Class Center Accuracy: 0.9525

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 15.764460563659668
Linear Weight Rank: 3670
Intra Cos: 0.6026299595832825
Inter Cos: 0.3046770691871643
Norm Quadratic Average: 24.85651206970215
Nearest Class Center Accuracy: 0.9595

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9418796300888062
Linear Weight Rank: 10
Intra Cos: 0.6231444478034973
Inter Cos: 0.2838788628578186
Norm Quadratic Average: 18.60568618774414
Nearest Class Center Accuracy: 0.9585

Output Layer:
Intra Cos: 0.6469760537147522
Inter Cos: 0.34915465116500854
Norm Quadratic Average: 14.284476280212402
Nearest Class Center Accuracy: 0.958

