Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_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: 0.08946067094802856
Inter Cos: 0.11311887204647064
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: 0.11147332936525345
Inter Cos: 0.1291806697845459
Norm Quadratic Average: 44.98288345336914
Nearest Class Center Accuracy: 0.823125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15778931975364685
Inter Cos: 0.16364836692810059
Norm Quadratic Average: 42.06735610961914
Nearest Class Center Accuracy: 0.816625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17868658900260925
Inter Cos: 0.1792565882205963
Norm Quadratic Average: 53.96133804321289
Nearest Class Center Accuracy: 0.83125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19781577587127686
Inter Cos: 0.17748376727104187
Norm Quadratic Average: 35.55735778808594
Nearest Class Center Accuracy: 0.86575

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22678594291210175
Inter Cos: 0.1921185404062271
Norm Quadratic Average: 33.786746978759766
Nearest Class Center Accuracy: 0.910375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.299311101436615
Inter Cos: 0.17865248024463654
Norm Quadratic Average: 20.290855407714844
Nearest Class Center Accuracy: 0.950875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.42470625042915344
Inter Cos: 0.2259429395198822
Norm Quadratic Average: 15.866029739379883
Nearest Class Center Accuracy: 0.98325

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.63890838623047
Linear Weight Rank: 4031
Intra Cos: 0.6486003994941711
Inter Cos: 0.26668781042099
Norm Quadratic Average: 70.62841033935547
Nearest Class Center Accuracy: 0.99825

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.072208404541016
Linear Weight Rank: 3671
Intra Cos: 0.7384650111198425
Inter Cos: 0.2652525007724762
Norm Quadratic Average: 45.82339096069336
Nearest Class Center Accuracy: 0.999625

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.450188398361206
Linear Weight Rank: 10
Intra Cos: 0.7743736505508423
Inter Cos: 0.25834375619888306
Norm Quadratic Average: 35.52432632446289
Nearest Class Center Accuracy: 0.99975

Output Layer:
Intra Cos: 0.8018980622291565
Inter Cos: 0.31632402539253235
Norm Quadratic Average: 25.76861572265625
Nearest Class Center Accuracy: 0.999875

Test Set:
Average Loss: 0.08164784942567349
Accuracy: 0.98
NC1 Within Class Collapse: 1.7085202932357788
NC2 Equinorm: Features: 0.11360456794500351, Weights: 0.01299496740102768
NC2 Equiangle: Features: 0.24686830308702257, Weights: 0.09905221727159289
NC3 Self-Duality: 0.530399739742279
NC4 NCC Mismatch: 0.010499999999999954

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133805871009827
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: 0.13245177268981934
Inter Cos: 0.1459934115409851
Norm Quadratic Average: 44.131309509277344
Nearest Class Center Accuracy: 0.8155

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17128102481365204
Inter Cos: 0.20074030756950378
Norm Quadratic Average: 41.34280776977539
Nearest Class Center Accuracy: 0.8175

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1777837872505188
Inter Cos: 0.21733102202415466
Norm Quadratic Average: 53.02669906616211
Nearest Class Center Accuracy: 0.829

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17957229912281036
Inter Cos: 0.20893225073814392
Norm Quadratic Average: 34.93040466308594
Nearest Class Center Accuracy: 0.856

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20639100670814514
Inter Cos: 0.22346976399421692
Norm Quadratic Average: 33.25706481933594
Nearest Class Center Accuracy: 0.897

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27092716097831726
Inter Cos: 0.18485711514949799
Norm Quadratic Average: 19.919782638549805
Nearest Class Center Accuracy: 0.935

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.37649625539779663
Inter Cos: 0.2185640037059784
Norm Quadratic Average: 15.516772270202637
Nearest Class Center Accuracy: 0.959

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.63890838623047
Linear Weight Rank: 4031
Intra Cos: 0.5813876390457153
Inter Cos: 0.2434944063425064
Norm Quadratic Average: 68.58565521240234
Nearest Class Center Accuracy: 0.9735

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.072208404541016
Linear Weight Rank: 3671
Intra Cos: 0.6636728644371033
Inter Cos: 0.24254581332206726
Norm Quadratic Average: 44.41398620605469
Nearest Class Center Accuracy: 0.9765

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.450188398361206
Linear Weight Rank: 10
Intra Cos: 0.6942930817604065
Inter Cos: 0.2563764452934265
Norm Quadratic Average: 34.46435546875
Nearest Class Center Accuracy: 0.977

Output Layer:
Intra Cos: 0.7111005187034607
Inter Cos: 0.3501932919025421
Norm Quadratic Average: 24.992076873779297
Nearest Class Center Accuracy: 0.9765

