Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_979323_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: 23.532934188842773
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11877728253602982
Inter Cos: 0.13871227204799652
Norm Quadratic Average: 45.13942337036133
Nearest Class Center Accuracy: 0.81575

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1638461947441101
Inter Cos: 0.1721416562795639
Norm Quadratic Average: 44.44333267211914
Nearest Class Center Accuracy: 0.798375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17784065008163452
Inter Cos: 0.18682828545570374
Norm Quadratic Average: 56.538795471191406
Nearest Class Center Accuracy: 0.806375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18857009708881378
Inter Cos: 0.1823861300945282
Norm Quadratic Average: 35.601646423339844
Nearest Class Center Accuracy: 0.848

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21513721346855164
Inter Cos: 0.2007787823677063
Norm Quadratic Average: 31.78329086303711
Nearest Class Center Accuracy: 0.890375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2979111075401306
Inter Cos: 0.1915419101715088
Norm Quadratic Average: 17.429725646972656
Nearest Class Center Accuracy: 0.93625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.42767783999443054
Inter Cos: 0.21432428061962128
Norm Quadratic Average: 12.981093406677246
Nearest Class Center Accuracy: 0.972625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.79407501220703
Linear Weight Rank: 4031
Intra Cos: 0.6585224270820618
Inter Cos: 0.2400008738040924
Norm Quadratic Average: 56.7855110168457
Nearest Class Center Accuracy: 0.997125

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.50033187866211
Linear Weight Rank: 3670
Intra Cos: 0.762115478515625
Inter Cos: 0.2632654011249542
Norm Quadratic Average: 37.136962890625
Nearest Class Center Accuracy: 0.99975

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.3469645977020264
Linear Weight Rank: 10
Intra Cos: 0.8024849891662598
Inter Cos: 0.2742014527320862
Norm Quadratic Average: 29.20476722717285
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8389924764633179
Inter Cos: 0.37320148944854736
Norm Quadratic Average: 21.21925163269043
Nearest Class Center Accuracy: 0.99975

Test Set:
Average Loss: 0.06786754348874093
Accuracy: 0.9805
NC1 Within Class Collapse: 1.9259158372879028
NC2 Equinorm: Features: 0.09328475594520569, Weights: 0.013633036985993385
NC2 Equiangle: Features: 0.25142960018581817, Weights: 0.1013421376546224
NC3 Self-Duality: 0.4635748565196991
NC4 NCC Mismatch: 0.01200000000000001

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133805871009827
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: 0.13397973775863647
Inter Cos: 0.15073108673095703
Norm Quadratic Average: 43.81519317626953
Nearest Class Center Accuracy: 0.811

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16797108948230743
Inter Cos: 0.19812574982643127
Norm Quadratic Average: 43.19367218017578
Nearest Class Center Accuracy: 0.795

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1763623058795929
Inter Cos: 0.22271685302257538
Norm Quadratic Average: 54.83578872680664
Nearest Class Center Accuracy: 0.809

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17027512192726135
Inter Cos: 0.2184094786643982
Norm Quadratic Average: 34.63140869140625
Nearest Class Center Accuracy: 0.838

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19438137114048004
Inter Cos: 0.23720292747020721
Norm Quadratic Average: 30.969661712646484
Nearest Class Center Accuracy: 0.8795

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26410144567489624
Inter Cos: 0.22916285693645477
Norm Quadratic Average: 16.946945190429688
Nearest Class Center Accuracy: 0.933

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.37954992055892944
Inter Cos: 0.2537943422794342
Norm Quadratic Average: 12.542546272277832
Nearest Class Center Accuracy: 0.9555

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.79407501220703
Linear Weight Rank: 4031
Intra Cos: 0.589017391204834
Inter Cos: 0.285145103931427
Norm Quadratic Average: 54.49668884277344
Nearest Class Center Accuracy: 0.9685

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.50033187866211
Linear Weight Rank: 3670
Intra Cos: 0.6908764839172363
Inter Cos: 0.2753012776374817
Norm Quadratic Average: 35.554386138916016
Nearest Class Center Accuracy: 0.9755

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.3469645977020264
Linear Weight Rank: 10
Intra Cos: 0.7292489409446716
Inter Cos: 0.27138960361480713
Norm Quadratic Average: 27.959877014160156
Nearest Class Center Accuracy: 0.9755

Output Layer:
Intra Cos: 0.7602584958076477
Inter Cos: 0.3460092544555664
Norm Quadratic Average: 20.29821014404297
Nearest Class Center Accuracy: 0.975

