Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_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: 0.08946067094802856
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: 0.11146707087755203
Inter Cos: 0.13541658222675323
Norm Quadratic Average: 46.13398742675781
Nearest Class Center Accuracy: 0.818125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14731130003929138
Inter Cos: 0.16892671585083008
Norm Quadratic Average: 46.83622741699219
Nearest Class Center Accuracy: 0.802625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16050775349140167
Inter Cos: 0.1855156421661377
Norm Quadratic Average: 62.764549255371094
Nearest Class Center Accuracy: 0.811625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1945340782403946
Inter Cos: 0.188795268535614
Norm Quadratic Average: 40.008399963378906
Nearest Class Center Accuracy: 0.84925

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22636708617210388
Inter Cos: 0.20271256566047668
Norm Quadratic Average: 39.36186981201172
Nearest Class Center Accuracy: 0.88425

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27282214164733887
Inter Cos: 0.17990003526210785
Norm Quadratic Average: 23.189844131469727
Nearest Class Center Accuracy: 0.931375

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.389773964881897
Inter Cos: 0.21035434305667877
Norm Quadratic Average: 17.914932250976562
Nearest Class Center Accuracy: 0.974875

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.93175506591797
Linear Weight Rank: 4031
Intra Cos: 0.6176177263259888
Inter Cos: 0.23558096587657928
Norm Quadratic Average: 78.37386322021484
Nearest Class Center Accuracy: 0.99775

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.39531326293945
Linear Weight Rank: 3670
Intra Cos: 0.7218576669692993
Inter Cos: 0.263431191444397
Norm Quadratic Average: 50.856849670410156
Nearest Class Center Accuracy: 0.999375

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.503429651260376
Linear Weight Rank: 10
Intra Cos: 0.7758458852767944
Inter Cos: 0.2706403434276581
Norm Quadratic Average: 39.953697204589844
Nearest Class Center Accuracy: 0.999625

Output Layer:
Intra Cos: 0.8223971128463745
Inter Cos: 0.40083450078964233
Norm Quadratic Average: 29.134183883666992
Nearest Class Center Accuracy: 0.999875

Test Set:
Average Loss: 0.08891941140592098
Accuracy: 0.9795
NC1 Within Class Collapse: 1.7544519901275635
NC2 Equinorm: Features: 0.12015896290540695, Weights: 0.013595441356301308
NC2 Equiangle: Features: 0.237374390496148, Weights: 0.09444317287868924
NC3 Self-Duality: 0.5489605069160461
NC4 NCC Mismatch: 0.01100000000000001

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: 0.13499926030635834
Inter Cos: 0.15045197308063507
Norm Quadratic Average: 44.97637176513672
Nearest Class Center Accuracy: 0.8135

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17056642472743988
Inter Cos: 0.19756969809532166
Norm Quadratic Average: 45.717979431152344
Nearest Class Center Accuracy: 0.7965

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18087613582611084
Inter Cos: 0.22180674970149994
Norm Quadratic Average: 61.17648696899414
Nearest Class Center Accuracy: 0.815

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1728292852640152
Inter Cos: 0.2223522663116455
Norm Quadratic Average: 39.11178207397461
Nearest Class Center Accuracy: 0.8475

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19510866701602936
Inter Cos: 0.23606735467910767
Norm Quadratic Average: 38.467803955078125
Nearest Class Center Accuracy: 0.88

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24118490517139435
Inter Cos: 0.2072821855545044
Norm Quadratic Average: 22.673831939697266
Nearest Class Center Accuracy: 0.924

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3412209153175354
Inter Cos: 0.24269600212574005
Norm Quadratic Average: 17.457029342651367
Nearest Class Center Accuracy: 0.954

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.93175506591797
Linear Weight Rank: 4031
Intra Cos: 0.5478513836860657
Inter Cos: 0.27367204427719116
Norm Quadratic Average: 76.0314712524414
Nearest Class Center Accuracy: 0.9745

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.39531326293945
Linear Weight Rank: 3670
Intra Cos: 0.6428022980690002
Inter Cos: 0.2766905725002289
Norm Quadratic Average: 49.22684860229492
Nearest Class Center Accuracy: 0.976

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.503429651260376
Linear Weight Rank: 10
Intra Cos: 0.6899005770683289
Inter Cos: 0.30253589153289795
Norm Quadratic Average: 38.72035598754883
Nearest Class Center Accuracy: 0.9735

Output Layer:
Intra Cos: 0.7262001633644104
Inter Cos: 0.4282417297363281
Norm Quadratic Average: 28.21000862121582
Nearest Class Center Accuracy: 0.97

