Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_weight_decay_0.007.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946066349744797
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: 0.10018783807754517
Inter Cos: 0.11872649192810059
Norm Quadratic Average: 62.85791778564453
Nearest Class Center Accuracy: 0.8365

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1396668404340744
Inter Cos: 0.13701462745666504
Norm Quadratic Average: 41.30651092529297
Nearest Class Center Accuracy: 0.84625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14001667499542236
Inter Cos: 0.12473541498184204
Norm Quadratic Average: 41.09113693237305
Nearest Class Center Accuracy: 0.86825

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16798019409179688
Inter Cos: 0.09858265519142151
Norm Quadratic Average: 25.43644142150879
Nearest Class Center Accuracy: 0.907375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17954647541046143
Inter Cos: 0.09413417428731918
Norm Quadratic Average: 25.803627014160156
Nearest Class Center Accuracy: 0.93825

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2084244340658188
Inter Cos: 0.10609851032495499
Norm Quadratic Average: 17.496826171875
Nearest Class Center Accuracy: 0.983375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3375777304172516
Inter Cos: 0.11639910191297531
Norm Quadratic Average: 13.507948875427246
Nearest Class Center Accuracy: 0.998625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.4433822631836
Linear Weight Rank: 4031
Intra Cos: 0.5934286713600159
Inter Cos: 0.12224666774272919
Norm Quadratic Average: 94.52771759033203
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.301420211791992
Linear Weight Rank: 3671
Intra Cos: 0.7481780052185059
Inter Cos: 0.140854150056839
Norm Quadratic Average: 45.45161819458008
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8324313163757324
Linear Weight Rank: 10
Intra Cos: 0.8433921933174133
Inter Cos: 0.18220193684101105
Norm Quadratic Average: 26.596935272216797
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9155105352401733
Inter Cos: 0.24889332056045532
Norm Quadratic Average: 13.694960594177246
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.07662908869981766
Accuracy: 0.977
NC1 Within Class Collapse: 1.5080881118774414
NC2 Equinorm: Features: 0.0618273988366127, Weights: 0.015716060996055603
NC2 Equiangle: Features: 0.19680603875054253, Weights: 0.08300350507100424
NC3 Self-Duality: 0.463268518447876
NC4 NCC Mismatch: 0.008499999999999952

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
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: 0.12082796543836594
Inter Cos: 0.12615880370140076
Norm Quadratic Average: 62.185768127441406
Nearest Class Center Accuracy: 0.829

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15131506323814392
Inter Cos: 0.1506543755531311
Norm Quadratic Average: 40.982513427734375
Nearest Class Center Accuracy: 0.8385

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15273433923721313
Inter Cos: 0.13765834271907806
Norm Quadratic Average: 40.75681686401367
Nearest Class Center Accuracy: 0.86

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16822868585586548
Inter Cos: 0.12855857610702515
Norm Quadratic Average: 25.373750686645508
Nearest Class Center Accuracy: 0.904

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18049275875091553
Inter Cos: 0.11675933003425598
Norm Quadratic Average: 25.789226531982422
Nearest Class Center Accuracy: 0.9235

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20877784490585327
Inter Cos: 0.11283037066459656
Norm Quadratic Average: 17.519821166992188
Nearest Class Center Accuracy: 0.9545

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2850390076637268
Inter Cos: 0.12292129546403885
Norm Quadratic Average: 13.408660888671875
Nearest Class Center Accuracy: 0.969

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 72.4433822631836
Linear Weight Rank: 4031
Intra Cos: 0.48882442712783813
Inter Cos: 0.1415737271308899
Norm Quadratic Average: 92.46771240234375
Nearest Class Center Accuracy: 0.9735

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 29.301420211791992
Linear Weight Rank: 3671
Intra Cos: 0.6269035339355469
Inter Cos: 0.1659090369939804
Norm Quadratic Average: 44.197696685791016
Nearest Class Center Accuracy: 0.974

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.8324313163757324
Linear Weight Rank: 10
Intra Cos: 0.7210943102836609
Inter Cos: 0.20816221833229065
Norm Quadratic Average: 25.809268951416016
Nearest Class Center Accuracy: 0.9745

Output Layer:
Intra Cos: 0.7957549095153809
Inter Cos: 0.255884051322937
Norm Quadratic Average: 13.262699127197266
Nearest Class Center Accuracy: 0.975

