Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.001.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116754680871964
Inter Cos: 0.10967153310775757
Norm Quadratic Average: 23.567678451538086
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09567290544509888
Inter Cos: 0.09664209187030792
Norm Quadratic Average: 3.73762845993042
Nearest Class Center Accuracy: 0.8637666666666667

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15547795593738556
Inter Cos: 0.11298344284296036
Norm Quadratic Average: 2.2565078735351562
Nearest Class Center Accuracy: 0.9212333333333333

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18252502381801605
Inter Cos: 0.11536417156457901
Norm Quadratic Average: 1.638168454170227
Nearest Class Center Accuracy: 0.9533666666666667

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2600480616092682
Inter Cos: 0.10143866389989853
Norm Quadratic Average: 1.1763471364974976
Nearest Class Center Accuracy: 0.9903833333333333

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.47903475165367126
Inter Cos: 0.13370825350284576
Norm Quadratic Average: 0.8897082805633545
Nearest Class Center Accuracy: 0.9989166666666667

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7056742906570435
Inter Cos: 0.057129472494125366
Norm Quadratic Average: 0.7597876191139221
Nearest Class Center Accuracy: 1.0

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9610899686813354
Inter Cos: 0.0367438904941082
Norm Quadratic Average: 1.0188686847686768
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.098890781402588
Linear Weight Rank: 4028
Intra Cos: 0.9960457682609558
Inter Cos: -0.017101159319281578
Norm Quadratic Average: 25.797597885131836
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.4701738357543945
Linear Weight Rank: 3637
Intra Cos: 0.9976379871368408
Inter Cos: 0.007357644848525524
Norm Quadratic Average: 18.604400634765625
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2959601879119873
Linear Weight Rank: 9
Intra Cos: 0.9979574084281921
Inter Cos: 0.019432444125413895
Norm Quadratic Average: 13.534916877746582
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9983491897583008
Inter Cos: 0.05815054848790169
Norm Quadratic Average: 10.49581241607666
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.015794649956189098
Accuracy: 0.9953
NC1 Within Class Collapse: 0.11009792983531952
NC2 Equinorm: Features: 0.020356303080916405, Weights: 0.0070806946605443954
NC2 Equiangle: Features: 0.07018540170457628, Weights: 0.03453414969974094
NC3 Self-Duality: 0.012591048143804073
NC4 NCC Mismatch: 0.00019999999999997797

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582915306091
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: 0.1051938459277153
Inter Cos: 0.09825260937213898
Norm Quadratic Average: 3.712130069732666
Nearest Class Center Accuracy: 0.8761

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16549070179462433
Inter Cos: 0.11265911906957626
Norm Quadratic Average: 2.241652011871338
Nearest Class Center Accuracy: 0.9297

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1936364620923996
Inter Cos: 0.11471554636955261
Norm Quadratic Average: 1.6308284997940063
Nearest Class Center Accuracy: 0.956

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2691948115825653
Inter Cos: 0.0998486801981926
Norm Quadratic Average: 1.1723419427871704
Nearest Class Center Accuracy: 0.9869

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.48691534996032715
Inter Cos: 0.13359443843364716
Norm Quadratic Average: 0.8873270153999329
Nearest Class Center Accuracy: 0.9932

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.7032345533370972
Inter Cos: 0.05793396756052971
Norm Quadratic Average: 0.7581803798675537
Nearest Class Center Accuracy: 0.9949

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9502089619636536
Inter Cos: 0.04557809606194496
Norm Quadratic Average: 1.0137851238250732
Nearest Class Center Accuracy: 0.9951

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.098890781402588
Linear Weight Rank: 4028
Intra Cos: 0.9764494299888611
Inter Cos: -0.00467140506953001
Norm Quadratic Average: 25.634822845458984
Nearest Class Center Accuracy: 0.9953

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.4701738357543945
Linear Weight Rank: 3637
Intra Cos: 0.9788047075271606
Inter Cos: 0.020201539620757103
Norm Quadratic Average: 18.486339569091797
Nearest Class Center Accuracy: 0.9953

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2959601879119873
Linear Weight Rank: 9
Intra Cos: 0.9795346856117249
Inter Cos: 0.03236604481935501
Norm Quadratic Average: 13.449898719787598
Nearest Class Center Accuracy: 0.9953

Output Layer:
Intra Cos: 0.9808758497238159
Inter Cos: 0.07113534212112427
Norm Quadratic Average: 10.430193901062012
Nearest Class Center Accuracy: 0.9954

