Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_weight_decay_0.005.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: 0.11613339930772781
Inter Cos: 0.13724344968795776
Norm Quadratic Average: 44.39852523803711
Nearest Class Center Accuracy: 0.819

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15351535379886627
Inter Cos: 0.17469516396522522
Norm Quadratic Average: 45.11028289794922
Nearest Class Center Accuracy: 0.792375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16550762951374054
Inter Cos: 0.18788577616214752
Norm Quadratic Average: 57.33073806762695
Nearest Class Center Accuracy: 0.794375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18344458937644958
Inter Cos: 0.19375552237033844
Norm Quadratic Average: 34.9224967956543
Nearest Class Center Accuracy: 0.836375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20388467609882355
Inter Cos: 0.2308291345834732
Norm Quadratic Average: 30.102699279785156
Nearest Class Center Accuracy: 0.87975

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27833086252212524
Inter Cos: 0.22090359032154083
Norm Quadratic Average: 16.00018310546875
Nearest Class Center Accuracy: 0.9305

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.41455867886543274
Inter Cos: 0.24808469414710999
Norm Quadratic Average: 11.40213680267334
Nearest Class Center Accuracy: 0.97125

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.76509094238281
Linear Weight Rank: 4031
Intra Cos: 0.6331660747528076
Inter Cos: 0.26901471614837646
Norm Quadratic Average: 49.89451599121094
Nearest Class Center Accuracy: 0.995125

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.25336456298828
Linear Weight Rank: 3670
Intra Cos: 0.7344067096710205
Inter Cos: 0.26781022548675537
Norm Quadratic Average: 33.075233459472656
Nearest Class Center Accuracy: 0.998875

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2648115158081055
Linear Weight Rank: 10
Intra Cos: 0.7720074653625488
Inter Cos: 0.26538464426994324
Norm Quadratic Average: 26.143110275268555
Nearest Class Center Accuracy: 0.999125

Output Layer:
Intra Cos: 0.8058689832687378
Inter Cos: 0.348838746547699
Norm Quadratic Average: 19.38577651977539
Nearest Class Center Accuracy: 0.998375

Test Set:
Average Loss: 0.07076721119880676
Accuracy: 0.9765
NC1 Within Class Collapse: 2.2076897621154785
NC2 Equinorm: Features: 0.11577527970075607, Weights: 0.018807685002684593
NC2 Equiangle: Features: 0.2626674652099609, Weights: 0.10786361694335937
NC3 Self-Duality: 0.4198666214942932
NC4 NCC Mismatch: 0.012499999999999956

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: 0.13687576353549957
Inter Cos: 0.15490682423114777
Norm Quadratic Average: 43.12113952636719
Nearest Class Center Accuracy: 0.8115

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1714843213558197
Inter Cos: 0.20760223269462585
Norm Quadratic Average: 43.785343170166016
Nearest Class Center Accuracy: 0.7935

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18388788402080536
Inter Cos: 0.2324194461107254
Norm Quadratic Average: 55.520626068115234
Nearest Class Center Accuracy: 0.7935

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16463476419448853
Inter Cos: 0.23248495161533356
Norm Quadratic Average: 33.96915054321289
Nearest Class Center Accuracy: 0.8345

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18244358897209167
Inter Cos: 0.265235960483551
Norm Quadratic Average: 29.352622985839844
Nearest Class Center Accuracy: 0.876

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24922288954257965
Inter Cos: 0.248215451836586
Norm Quadratic Average: 15.597260475158691
Nearest Class Center Accuracy: 0.926

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.36898139119148254
Inter Cos: 0.28177306056022644
Norm Quadratic Average: 11.05977725982666
Nearest Class Center Accuracy: 0.953

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.76509094238281
Linear Weight Rank: 4031
Intra Cos: 0.5587596893310547
Inter Cos: 0.3019062876701355
Norm Quadratic Average: 47.95480728149414
Nearest Class Center Accuracy: 0.9675

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.25336456298828
Linear Weight Rank: 3670
Intra Cos: 0.6504067778587341
Inter Cos: 0.2892102599143982
Norm Quadratic Average: 31.741477966308594
Nearest Class Center Accuracy: 0.9735

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2648115158081055
Linear Weight Rank: 10
Intra Cos: 0.6832048892974854
Inter Cos: 0.2557252049446106
Norm Quadratic Average: 25.11345672607422
Nearest Class Center Accuracy: 0.975

Output Layer:
Intra Cos: 0.7048183083534241
Inter Cos: 0.32291460037231445
Norm Quadratic Average: 18.59096908569336
Nearest Class Center Accuracy: 0.972

