Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_weight_decay_0.0007.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: 0.11446519196033478
Inter Cos: 0.1346845179796219
Norm Quadratic Average: 48.198246002197266
Nearest Class Center Accuracy: 0.8215

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15331105887889862
Inter Cos: 0.16993103921413422
Norm Quadratic Average: 46.80868148803711
Nearest Class Center Accuracy: 0.80175

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1668834090232849
Inter Cos: 0.18165314197540283
Norm Quadratic Average: 61.18666076660156
Nearest Class Center Accuracy: 0.809

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1814214438199997
Inter Cos: 0.18053287267684937
Norm Quadratic Average: 39.44953918457031
Nearest Class Center Accuracy: 0.852

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2021123319864273
Inter Cos: 0.20943579077720642
Norm Quadratic Average: 38.471031188964844
Nearest Class Center Accuracy: 0.8935

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26531076431274414
Inter Cos: 0.19186027348041534
Norm Quadratic Average: 22.664213180541992
Nearest Class Center Accuracy: 0.936375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.38512909412384033
Inter Cos: 0.2173149734735489
Norm Quadratic Average: 17.79611587524414
Nearest Class Center Accuracy: 0.97425

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.03587341308594
Linear Weight Rank: 4031
Intra Cos: 0.6070746779441833
Inter Cos: 0.2429998219013214
Norm Quadratic Average: 78.04808044433594
Nearest Class Center Accuracy: 0.99725

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.623329162597656
Linear Weight Rank: 3670
Intra Cos: 0.719984233379364
Inter Cos: 0.24450084567070007
Norm Quadratic Average: 50.225364685058594
Nearest Class Center Accuracy: 0.9995

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.45989727973938
Linear Weight Rank: 10
Intra Cos: 0.7734464406967163
Inter Cos: 0.2514427900314331
Norm Quadratic Average: 38.85551452636719
Nearest Class Center Accuracy: 0.99975

Output Layer:
Intra Cos: 0.8237382173538208
Inter Cos: 0.35266539454460144
Norm Quadratic Average: 27.853294372558594
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.08179550448060036
Accuracy: 0.979
NC1 Within Class Collapse: 1.8579273223876953
NC2 Equinorm: Features: 0.10579349845647812, Weights: 0.013076997362077236
NC2 Equiangle: Features: 0.24468820359971788, Weights: 0.09827375411987305
NC3 Self-Duality: 0.5429288148880005
NC4 NCC Mismatch: 0.014000000000000012

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: 0.1351671665906906
Inter Cos: 0.15140365064144135
Norm Quadratic Average: 46.86888885498047
Nearest Class Center Accuracy: 0.814

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17093101143836975
Inter Cos: 0.20040033757686615
Norm Quadratic Average: 45.5037727355957
Nearest Class Center Accuracy: 0.801

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18043798208236694
Inter Cos: 0.22147585451602936
Norm Quadratic Average: 59.34157180786133
Nearest Class Center Accuracy: 0.8135

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16332320868968964
Inter Cos: 0.21734654903411865
Norm Quadratic Average: 38.43480682373047
Nearest Class Center Accuracy: 0.844

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18037623167037964
Inter Cos: 0.24243777990341187
Norm Quadratic Average: 37.54072570800781
Nearest Class Center Accuracy: 0.889

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23645715415477753
Inter Cos: 0.21671722829341888
Norm Quadratic Average: 22.099441528320312
Nearest Class Center Accuracy: 0.9285

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3376346230506897
Inter Cos: 0.2470513880252838
Norm Quadratic Average: 17.235225677490234
Nearest Class Center Accuracy: 0.953

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.03587341308594
Linear Weight Rank: 4031
Intra Cos: 0.5266337394714355
Inter Cos: 0.26919108629226685
Norm Quadratic Average: 74.89546203613281
Nearest Class Center Accuracy: 0.9695

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.623329162597656
Linear Weight Rank: 3670
Intra Cos: 0.6291080713272095
Inter Cos: 0.26323795318603516
Norm Quadratic Average: 48.106361389160156
Nearest Class Center Accuracy: 0.9745

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.45989727973938
Linear Weight Rank: 10
Intra Cos: 0.6770763993263245
Inter Cos: 0.2410746067762375
Norm Quadratic Average: 37.241390228271484
Nearest Class Center Accuracy: 0.9735

Output Layer:
Intra Cos: 0.7141427993774414
Inter Cos: 0.32788488268852234
Norm Quadratic Average: 26.66024398803711
Nearest Class Center Accuracy: 0.972

