Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_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: 0.08946066349744797
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: 0.10405108332633972
Inter Cos: 0.1266169548034668
Norm Quadratic Average: 20.558074951171875
Nearest Class Center Accuracy: 0.83325

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15086133778095245
Inter Cos: 0.13806581497192383
Norm Quadratic Average: 13.326807022094727
Nearest Class Center Accuracy: 0.860875

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15487876534461975
Inter Cos: 0.13481394946575165
Norm Quadratic Average: 13.438560485839844
Nearest Class Center Accuracy: 0.881

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20618653297424316
Inter Cos: 0.12175480276346207
Norm Quadratic Average: 8.099882125854492
Nearest Class Center Accuracy: 0.93775

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2392740547657013
Inter Cos: 0.11027538031339645
Norm Quadratic Average: 8.380914688110352
Nearest Class Center Accuracy: 0.973375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3567928671836853
Inter Cos: 0.13583208620548248
Norm Quadratic Average: 5.676929473876953
Nearest Class Center Accuracy: 0.99825

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6913971900939941
Inter Cos: 0.16625361144542694
Norm Quadratic Average: 4.587408542633057
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 23.996875762939453
Linear Weight Rank: 4031
Intra Cos: 0.9440631866455078
Inter Cos: 0.17670369148254395
Norm Quadratic Average: 52.667442321777344
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.787537574768066
Linear Weight Rank: 3670
Intra Cos: 0.9810817837715149
Inter Cos: 0.22001944482326508
Norm Quadratic Average: 25.64362335205078
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5648760795593262
Linear Weight Rank: 10
Intra Cos: 0.9807103872299194
Inter Cos: 0.22980470955371857
Norm Quadratic Average: 14.647401809692383
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9802606701850891
Inter Cos: 0.32120227813720703
Norm Quadratic Average: 8.885734558105469
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.07071581149101257
Accuracy: 0.983
NC1 Within Class Collapse: 0.8427852988243103
NC2 Equinorm: Features: 0.0827312022447586, Weights: 0.020270470529794693
NC2 Equiangle: Features: 0.2295718722873264, Weights: 0.13555340237087674
NC3 Self-Duality: 0.09892770648002625
NC4 NCC Mismatch: 0.0020000000000000018

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957791447639465
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: 0.1285858154296875
Inter Cos: 0.13338316977024078
Norm Quadratic Average: 20.274011611938477
Nearest Class Center Accuracy: 0.8275

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16423961520195007
Inter Cos: 0.15816792845726013
Norm Quadratic Average: 13.245789527893066
Nearest Class Center Accuracy: 0.8545

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16892406344413757
Inter Cos: 0.1512010544538498
Norm Quadratic Average: 13.349971771240234
Nearest Class Center Accuracy: 0.877

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.197139710187912
Inter Cos: 0.12915699183940887
Norm Quadratic Average: 8.070234298706055
Nearest Class Center Accuracy: 0.927

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2393234372138977
Inter Cos: 0.12876653671264648
Norm Quadratic Average: 8.373419761657715
Nearest Class Center Accuracy: 0.9525

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3269154727458954
Inter Cos: 0.12776526808738708
Norm Quadratic Average: 5.63551139831543
Nearest Class Center Accuracy: 0.9765

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6155236959457397
Inter Cos: 0.1721053123474121
Norm Quadratic Average: 4.481232166290283
Nearest Class Center Accuracy: 0.983

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 23.996875762939453
Linear Weight Rank: 4031
Intra Cos: 0.8533104062080383
Inter Cos: 0.1981697380542755
Norm Quadratic Average: 50.37032699584961
Nearest Class Center Accuracy: 0.982

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.787537574768066
Linear Weight Rank: 3670
Intra Cos: 0.8830474019050598
Inter Cos: 0.23729437589645386
Norm Quadratic Average: 24.548778533935547
Nearest Class Center Accuracy: 0.9835

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5648760795593262
Linear Weight Rank: 10
Intra Cos: 0.8713588118553162
Inter Cos: 0.21432222425937653
Norm Quadratic Average: 14.077353477478027
Nearest Class Center Accuracy: 0.9835

Output Layer:
Intra Cos: 0.8615438938140869
Inter Cos: 0.3010375499725342
Norm Quadratic Average: 8.540750503540039
Nearest Class Center Accuracy: 0.9835

