Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_weight_decay_0.0005.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: 0.11311887204647064
Norm Quadratic Average: 23.532934188842773
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11154423654079437
Inter Cos: 0.13546031713485718
Norm Quadratic Average: 45.882259368896484
Nearest Class Center Accuracy: 0.81825

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14745096862316132
Inter Cos: 0.16898006200790405
Norm Quadratic Average: 46.46420669555664
Nearest Class Center Accuracy: 0.8025

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16078068315982819
Inter Cos: 0.18642009794712067
Norm Quadratic Average: 61.80447769165039
Nearest Class Center Accuracy: 0.812

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19535015523433685
Inter Cos: 0.19037781655788422
Norm Quadratic Average: 39.2775993347168
Nearest Class Center Accuracy: 0.849625

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22744819521903992
Inter Cos: 0.20590977370738983
Norm Quadratic Average: 38.26062774658203
Nearest Class Center Accuracy: 0.88575

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27680808305740356
Inter Cos: 0.1841965615749359
Norm Quadratic Average: 22.466236114501953
Nearest Class Center Accuracy: 0.93025

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3944578170776367
Inter Cos: 0.21168212592601776
Norm Quadratic Average: 17.310955047607422
Nearest Class Center Accuracy: 0.974125

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.97836303710938
Linear Weight Rank: 4031
Intra Cos: 0.6173219680786133
Inter Cos: 0.2335270196199417
Norm Quadratic Average: 75.86365509033203
Nearest Class Center Accuracy: 0.997875

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.0104866027832
Linear Weight Rank: 3670
Intra Cos: 0.724469006061554
Inter Cos: 0.2533307373523712
Norm Quadratic Average: 49.255279541015625
Nearest Class Center Accuracy: 0.999625

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4899179935455322
Linear Weight Rank: 10
Intra Cos: 0.7779541611671448
Inter Cos: 0.26357901096343994
Norm Quadratic Average: 38.67666244506836
Nearest Class Center Accuracy: 0.99975

Output Layer:
Intra Cos: 0.8220415115356445
Inter Cos: 0.39092543721199036
Norm Quadratic Average: 28.190149307250977
Nearest Class Center Accuracy: 0.99975

Test Set:
Average Loss: 0.08437780879437923
Accuracy: 0.981
NC1 Within Class Collapse: 1.7384147644042969
NC2 Equinorm: Features: 0.12148880213499069, Weights: 0.013269775547087193
NC2 Equiangle: Features: 0.23738763597276474, Weights: 0.09442874060736763
NC3 Self-Duality: 0.5415375828742981
NC4 NCC Mismatch: 0.010499999999999954

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957792937755585
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: 0.13503684103488922
Inter Cos: 0.15054990351200104
Norm Quadratic Average: 44.730438232421875
Nearest Class Center Accuracy: 0.8135

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17093400657176971
Inter Cos: 0.19791358709335327
Norm Quadratic Average: 45.357608795166016
Nearest Class Center Accuracy: 0.7965

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18120510876178741
Inter Cos: 0.2224823534488678
Norm Quadratic Average: 60.236114501953125
Nearest Class Center Accuracy: 0.815

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1738501638174057
Inter Cos: 0.22343726456165314
Norm Quadratic Average: 38.40037155151367
Nearest Class Center Accuracy: 0.848

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19645604491233826
Inter Cos: 0.238755464553833
Norm Quadratic Average: 37.395362854003906
Nearest Class Center Accuracy: 0.879

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2436385154724121
Inter Cos: 0.2109755128622055
Norm Quadratic Average: 21.945343017578125
Nearest Class Center Accuracy: 0.9265

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.34609678387641907
Inter Cos: 0.24595104157924652
Norm Quadratic Average: 16.846635818481445
Nearest Class Center Accuracy: 0.955

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.97836303710938
Linear Weight Rank: 4031
Intra Cos: 0.5467562079429626
Inter Cos: 0.27339625358581543
Norm Quadratic Average: 73.46965026855469
Nearest Class Center Accuracy: 0.973

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.0104866027832
Linear Weight Rank: 3670
Intra Cos: 0.643924355506897
Inter Cos: 0.2769889235496521
Norm Quadratic Average: 47.57080078125
Nearest Class Center Accuracy: 0.9755

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.4899179935455322
Linear Weight Rank: 10
Intra Cos: 0.690730631351471
Inter Cos: 0.29994478821754456
Norm Quadratic Average: 37.412960052490234
Nearest Class Center Accuracy: 0.974

Output Layer:
Intra Cos: 0.7234925627708435
Inter Cos: 0.42217326164245605
Norm Quadratic Average: 27.253299713134766
Nearest Class Center Accuracy: 0.9695

