Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_weight_decay_0.03.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: 0.11311887949705124
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: 0.12269497662782669
Inter Cos: 0.14922074973583221
Norm Quadratic Average: 38.12748718261719
Nearest Class Center Accuracy: 0.80425

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1516919583082199
Inter Cos: 0.18376857042312622
Norm Quadratic Average: 45.28007125854492
Nearest Class Center Accuracy: 0.7645

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1589123010635376
Inter Cos: 0.2011367827653885
Norm Quadratic Average: 62.90915298461914
Nearest Class Center Accuracy: 0.749375

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16916339099407196
Inter Cos: 0.21502090990543365
Norm Quadratic Average: 41.33086013793945
Nearest Class Center Accuracy: 0.77975

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19041800498962402
Inter Cos: 0.2733571231365204
Norm Quadratic Average: 30.292421340942383
Nearest Class Center Accuracy: 0.835875

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27876636385917664
Inter Cos: 0.3019077777862549
Norm Quadratic Average: 16.441179275512695
Nearest Class Center Accuracy: 0.8865

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.42176762223243713
Inter Cos: 0.3539464771747589
Norm Quadratic Average: 10.02322006225586
Nearest Class Center Accuracy: 0.932625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 24.013463973999023
Linear Weight Rank: 4031
Intra Cos: 0.551974356174469
Inter Cos: 0.34303757548332214
Norm Quadratic Average: 41.374122619628906
Nearest Class Center Accuracy: 0.961375

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.82887077331543
Linear Weight Rank: 3669
Intra Cos: 0.6313778162002563
Inter Cos: 0.3307798504829407
Norm Quadratic Average: 26.924449920654297
Nearest Class Center Accuracy: 0.969875

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7942025661468506
Linear Weight Rank: 10
Intra Cos: 0.6633328199386597
Inter Cos: 0.3094179332256317
Norm Quadratic Average: 18.644594192504883
Nearest Class Center Accuracy: 0.971625

Output Layer:
Intra Cos: 0.7072639465332031
Inter Cos: 0.3559745252132416
Norm Quadratic Average: 13.813311576843262
Nearest Class Center Accuracy: 0.971375

Test Set:
Average Loss: 0.1284848449230194
Accuracy: 0.9625
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.17762427031993866, Weights: 0.041879765689373016
NC2 Equiangle: Features: 0.31255164676242403, Weights: 0.19480563269721138
NC3 Self-Duality: 0.19378991425037384
NC4 NCC Mismatch: 0.029000000000000026

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133808106184006
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: 0.1428382843732834
Inter Cos: 0.17081671953201294
Norm Quadratic Average: 36.79222869873047
Nearest Class Center Accuracy: 0.8035

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16323089599609375
Inter Cos: 0.21927422285079956
Norm Quadratic Average: 43.73151779174805
Nearest Class Center Accuracy: 0.7695

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17563685774803162
Inter Cos: 0.24587519466876984
Norm Quadratic Average: 60.628509521484375
Nearest Class Center Accuracy: 0.759

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15277153253555298
Inter Cos: 0.24961435794830322
Norm Quadratic Average: 39.95845031738281
Nearest Class Center Accuracy: 0.787

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1764165312051773
Inter Cos: 0.30213862657546997
Norm Quadratic Average: 29.362455368041992
Nearest Class Center Accuracy: 0.838

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.254193514585495
Inter Cos: 0.28998979926109314
Norm Quadratic Average: 15.85272216796875
Nearest Class Center Accuracy: 0.8775

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.37652862071990967
Inter Cos: 0.33460313081741333
Norm Quadratic Average: 9.614636421203613
Nearest Class Center Accuracy: 0.9125

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 24.013463973999023
Linear Weight Rank: 4031
Intra Cos: 0.4866303503513336
Inter Cos: 0.3238849639892578
Norm Quadratic Average: 39.67856979370117
Nearest Class Center Accuracy: 0.9385

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.82887077331543
Linear Weight Rank: 3669
Intra Cos: 0.5515214800834656
Inter Cos: 0.3097936511039734
Norm Quadratic Average: 25.828275680541992
Nearest Class Center Accuracy: 0.9495

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.7942025661468506
Linear Weight Rank: 10
Intra Cos: 0.5739133954048157
Inter Cos: 0.3033274710178375
Norm Quadratic Average: 17.907243728637695
Nearest Class Center Accuracy: 0.9495

Output Layer:
Intra Cos: 0.6004251837730408
Inter Cos: 0.38925495743751526
Norm Quadratic Average: 13.246635437011719
Nearest Class Center Accuracy: 0.95

