Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116753935813904
Inter Cos: 0.10967151820659637
Norm Quadratic Average: 23.567676544189453
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11692328006029129
Inter Cos: 0.1363665759563446
Norm Quadratic Average: 37.76442337036133
Nearest Class Center Accuracy: 0.8256666666666667

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18830052018165588
Inter Cos: 0.17040038108825684
Norm Quadratic Average: 35.64247512817383
Nearest Class Center Accuracy: 0.87755

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22081395983695984
Inter Cos: 0.18126416206359863
Norm Quadratic Average: 35.30596923828125
Nearest Class Center Accuracy: 0.9101833333333333

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24870766699314117
Inter Cos: 0.1641446352005005
Norm Quadratic Average: 16.654403686523438
Nearest Class Center Accuracy: 0.9565

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3860788345336914
Inter Cos: 0.2182905524969101
Norm Quadratic Average: 10.857414245605469
Nearest Class Center Accuracy: 0.9779

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5583697557449341
Inter Cos: 0.2568569779396057
Norm Quadratic Average: 5.52829122543335
Nearest Class Center Accuracy: 0.9936333333333334

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8172509074211121
Inter Cos: 0.3035772144794464
Norm Quadratic Average: 4.606712818145752
Nearest Class Center Accuracy: 0.99865

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 31.7237491607666
Linear Weight Rank: 4031
Intra Cos: 0.8981454968452454
Inter Cos: 0.2390003651380539
Norm Quadratic Average: 26.061264038085938
Nearest Class Center Accuracy: 0.9993666666666666

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 13.071513175964355
Linear Weight Rank: 3669
Intra Cos: 0.9267376661300659
Inter Cos: 0.210567444562912
Norm Quadratic Average: 23.32826805114746
Nearest Class Center Accuracy: 0.9998333333333334

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.775149345397949
Linear Weight Rank: 10
Intra Cos: 0.9320866465568542
Inter Cos: 0.1816549152135849
Norm Quadratic Average: 21.483821868896484
Nearest Class Center Accuracy: 0.9999333333333333

Output Layer:
Intra Cos: 0.9527105689048767
Inter Cos: 0.2771066427230835
Norm Quadratic Average: 21.795116424560547
Nearest Class Center Accuracy: 0.9999833333333333

Test Set:
Average Loss: 0.02125685010960733
Accuracy: 0.9938
NC1 Within Class Collapse: 0.5424462556838989
NC2 Equinorm: Features: 0.08363808691501617, Weights: 0.02648364007472992
NC2 Equiangle: Features: 0.21089867485894098, Weights: 0.11191532346937391
NC3 Self-Duality: 0.12702135741710663
NC4 NCC Mismatch: 0.0030000000000000027

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219582170248032
Inter Cos: 0.12048851698637009
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: 0.1293853372335434
Inter Cos: 0.14270830154418945
Norm Quadratic Average: 37.69657897949219
Nearest Class Center Accuracy: 0.8389

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20158804953098297
Inter Cos: 0.16776640713214874
Norm Quadratic Average: 35.51485061645508
Nearest Class Center Accuracy: 0.8897

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23361781239509583
Inter Cos: 0.18340489268302917
Norm Quadratic Average: 35.214962005615234
Nearest Class Center Accuracy: 0.9206

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2604304850101471
Inter Cos: 0.1785687506198883
Norm Quadratic Average: 16.62615966796875
Nearest Class Center Accuracy: 0.963

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.39981552958488464
Inter Cos: 0.23458550870418549
Norm Quadratic Average: 10.856423377990723
Nearest Class Center Accuracy: 0.9797

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.56561279296875
Inter Cos: 0.2723083198070526
Norm Quadratic Average: 5.553949356079102
Nearest Class Center Accuracy: 0.9889

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8192764520645142
Inter Cos: 0.3140839636325836
Norm Quadratic Average: 4.644209861755371
Nearest Class Center Accuracy: 0.9908

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 31.7237491607666
Linear Weight Rank: 4031
Intra Cos: 0.8950756788253784
Inter Cos: 0.244422048330307
Norm Quadratic Average: 26.26166343688965
Nearest Class Center Accuracy: 0.992

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 13.071513175964355
Linear Weight Rank: 3669
Intra Cos: 0.9228397011756897
Inter Cos: 0.2245044857263565
Norm Quadratic Average: 23.498538970947266
Nearest Class Center Accuracy: 0.9928

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.775149345397949
Linear Weight Rank: 10
Intra Cos: 0.9275997281074524
Inter Cos: 0.19562941789627075
Norm Quadratic Average: 21.63645362854004
Nearest Class Center Accuracy: 0.9928

Output Layer:
Intra Cos: 0.9446192383766174
Inter Cos: 0.2611084580421448
Norm Quadratic Average: 21.942737579345703
Nearest Class Center Accuracy: 0.9935

