Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_265358_test_samples_None_train_samples_None_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: 0.09116753190755844
Inter Cos: 0.10967151820659637
Norm Quadratic Average: 23.567670822143555
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09505287557840347
Inter Cos: 0.09650653600692749
Norm Quadratic Average: 2.225374937057495
Nearest Class Center Accuracy: 0.861

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.169484943151474
Inter Cos: 0.11730246990919113
Norm Quadratic Average: 1.3364784717559814
Nearest Class Center Accuracy: 0.9202833333333333

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.200220987200737
Inter Cos: 0.12595373392105103
Norm Quadratic Average: 1.0003304481506348
Nearest Class Center Accuracy: 0.9544666666666667

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2899593412876129
Inter Cos: 0.11284229159355164
Norm Quadratic Average: 0.6639189124107361
Nearest Class Center Accuracy: 0.9917333333333334

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5660362243652344
Inter Cos: 0.17088454961776733
Norm Quadratic Average: 0.5418931245803833
Nearest Class Center Accuracy: 0.9991166666666667

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8077781796455383
Inter Cos: 0.15465892851352692
Norm Quadratic Average: 0.6158685684204102
Nearest Class Center Accuracy: 1.0

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9795435667037964
Inter Cos: 0.03351622447371483
Norm Quadratic Average: 0.9795438051223755
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.2041144371032715
Linear Weight Rank: 165
Intra Cos: 0.9965596199035645
Inter Cos: 0.009635524824261665
Norm Quadratic Average: 25.143461227416992
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.208906888961792
Linear Weight Rank: 1392
Intra Cos: 0.9972744584083557
Inter Cos: 0.03747425973415375
Norm Quadratic Average: 17.406511306762695
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.205862045288086
Linear Weight Rank: 9
Intra Cos: 0.9975568056106567
Inter Cos: 0.04675178602337837
Norm Quadratic Average: 12.24273681640625
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9978942275047302
Inter Cos: 0.061679042875766754
Norm Quadratic Average: 9.103874206542969
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.015349784286320209
Accuracy: 0.9958
NC1 Within Class Collapse: 0.11663719266653061
NC2 Equinorm: Features: 0.01880086399614811, Weights: 0.005858549382537603
NC2 Equiangle: Features: 0.07040779855516222, Weights: 0.027903291914198134
NC3 Self-Duality: 0.011051258072257042
NC4 NCC Mismatch: 9.999999999998899e-05

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219583660364151
Inter Cos: 0.12048852443695068
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10417770594358444
Inter Cos: 0.09727321565151215
Norm Quadratic Average: 2.212273359298706
Nearest Class Center Accuracy: 0.8747

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1803043782711029
Inter Cos: 0.11629467457532883
Norm Quadratic Average: 1.329234004020691
Nearest Class Center Accuracy: 0.9283

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21281394362449646
Inter Cos: 0.12419044226408005
Norm Quadratic Average: 0.9962798953056335
Nearest Class Center Accuracy: 0.9576

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3001041114330292
Inter Cos: 0.12260923534631729
Norm Quadratic Average: 0.6610692739486694
Nearest Class Center Accuracy: 0.9886

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5717276930809021
Inter Cos: 0.18355506658554077
Norm Quadratic Average: 0.5404354333877563
Nearest Class Center Accuracy: 0.9935

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8005173206329346
Inter Cos: 0.16218119859695435
Norm Quadratic Average: 0.6140409708023071
Nearest Class Center Accuracy: 0.9956

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9675759673118591
Inter Cos: 0.04474524408578873
Norm Quadratic Average: 0.9750222563743591
Nearest Class Center Accuracy: 0.9959

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.2041144371032715
Linear Weight Rank: 165
Intra Cos: 0.9783119559288025
Inter Cos: 0.01825934648513794
Norm Quadratic Average: 25.014041900634766
Nearest Class Center Accuracy: 0.9959

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.208906888961792
Linear Weight Rank: 1392
Intra Cos: 0.9795229434967041
Inter Cos: 0.049823712557554245
Norm Quadratic Average: 17.317014694213867
Nearest Class Center Accuracy: 0.9959

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.205862045288086
Linear Weight Rank: 9
Intra Cos: 0.979955792427063
Inter Cos: 0.0588398315012455
Norm Quadratic Average: 12.179810523986816
Nearest Class Center Accuracy: 0.9959

Output Layer:
Intra Cos: 0.9807721972465515
Inter Cos: 0.07392475754022598
Norm Quadratic Average: 9.057212829589844
Nearest Class Center Accuracy: 0.996

