Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_weight_decay_0.003.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: 0.11525310575962067
Inter Cos: 0.1359102874994278
Norm Quadratic Average: 45.745235443115234
Nearest Class Center Accuracy: 0.820375

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1532457023859024
Inter Cos: 0.17262321710586548
Norm Quadratic Average: 45.08160400390625
Nearest Class Center Accuracy: 0.797375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1656331866979599
Inter Cos: 0.18515166640281677
Norm Quadratic Average: 57.601959228515625
Nearest Class Center Accuracy: 0.801375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1835697889328003
Inter Cos: 0.1883036345243454
Norm Quadratic Average: 35.87506866455078
Nearest Class Center Accuracy: 0.843125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20327036082744598
Inter Cos: 0.2205173373222351
Norm Quadratic Average: 32.63112258911133
Nearest Class Center Accuracy: 0.884875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2748364210128784
Inter Cos: 0.20975807309150696
Norm Quadratic Average: 18.089584350585938
Nearest Class Center Accuracy: 0.931875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4041488468647003
Inter Cos: 0.23479105532169342
Norm Quadratic Average: 13.420520782470703
Nearest Class Center Accuracy: 0.97175

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.79692077636719
Linear Weight Rank: 4031
Intra Cos: 0.6240667700767517
Inter Cos: 0.2524139881134033
Norm Quadratic Average: 58.67835998535156
Nearest Class Center Accuracy: 0.996375

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.49201965332031
Linear Weight Rank: 3670
Intra Cos: 0.7305834293365479
Inter Cos: 0.2500137984752655
Norm Quadratic Average: 38.242408752441406
Nearest Class Center Accuracy: 0.999375

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.333799362182617
Linear Weight Rank: 10
Intra Cos: 0.7749493718147278
Inter Cos: 0.2621139585971832
Norm Quadratic Average: 29.89606285095215
Nearest Class Center Accuracy: 0.9995

Output Layer:
Intra Cos: 0.8132219314575195
Inter Cos: 0.36005324125289917
Norm Quadratic Average: 21.708831787109375
Nearest Class Center Accuracy: 0.998875

Test Set:
Average Loss: 0.07148980700969695
Accuracy: 0.978
NC1 Within Class Collapse: 2.0288963317871094
NC2 Equinorm: Features: 0.10984597355127335, Weights: 0.014882979914546013
NC2 Equiangle: Features: 0.25530264112684464, Weights: 0.10262136459350586
NC3 Self-Duality: 0.47511181235313416
NC4 NCC Mismatch: 0.010499999999999954

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: 0.13604344427585602
Inter Cos: 0.1531068980693817
Norm Quadratic Average: 44.458126068115234
Nearest Class Center Accuracy: 0.813

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17160308361053467
Inter Cos: 0.20447319746017456
Norm Quadratic Average: 43.791107177734375
Nearest Class Center Accuracy: 0.7965

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18326738476753235
Inter Cos: 0.22777687013149261
Norm Quadratic Average: 55.83199691772461
Nearest Class Center Accuracy: 0.805

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16497789323329926
Inter Cos: 0.22661837935447693
Norm Quadratic Average: 34.942378997802734
Nearest Class Center Accuracy: 0.839

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18154901266098022
Inter Cos: 0.25456130504608154
Norm Quadratic Average: 31.845272064208984
Nearest Class Center Accuracy: 0.882

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24452552199363708
Inter Cos: 0.23546573519706726
Norm Quadratic Average: 17.654800415039062
Nearest Class Center Accuracy: 0.9235

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3566654324531555
Inter Cos: 0.2667820155620575
Norm Quadratic Average: 13.010468482971191
Nearest Class Center Accuracy: 0.9515

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.79692077636719
Linear Weight Rank: 4031
Intra Cos: 0.5479764342308044
Inter Cos: 0.2872808277606964
Norm Quadratic Average: 56.36023712158203
Nearest Class Center Accuracy: 0.9685

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.49201965332031
Linear Weight Rank: 3670
Intra Cos: 0.6444319486618042
Inter Cos: 0.27597931027412415
Norm Quadratic Average: 36.66796875
Nearest Class Center Accuracy: 0.974

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.333799362182617
Linear Weight Rank: 10
Intra Cos: 0.6838968992233276
Inter Cos: 0.2449144870042801
Norm Quadratic Average: 28.69036293029785
Nearest Class Center Accuracy: 0.9755

Output Layer:
Intra Cos: 0.7103054523468018
Inter Cos: 0.3334580361843109
Norm Quadratic Average: 20.80453109741211
Nearest Class Center Accuracy: 0.973

