Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_weight_decay_0.0001.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: 0.11431343108415604
Inter Cos: 0.1344282478094101
Norm Quadratic Average: 49.08320236206055
Nearest Class Center Accuracy: 0.82175

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1531822383403778
Inter Cos: 0.1693187803030014
Norm Quadratic Average: 47.90369415283203
Nearest Class Center Accuracy: 0.803

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1664523333311081
Inter Cos: 0.18096834421157837
Norm Quadratic Average: 63.48422622680664
Nearest Class Center Accuracy: 0.810125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18174590170383453
Inter Cos: 0.17860259115695953
Norm Quadratic Average: 41.558650970458984
Nearest Class Center Accuracy: 0.854125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2019311636686325
Inter Cos: 0.20550304651260376
Norm Quadratic Average: 41.281471252441406
Nearest Class Center Accuracy: 0.8945

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.263316810131073
Inter Cos: 0.19133935868740082
Norm Quadratic Average: 24.755905151367188
Nearest Class Center Accuracy: 0.938

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3820417821407318
Inter Cos: 0.21444520354270935
Norm Quadratic Average: 19.782236099243164
Nearest Class Center Accuracy: 0.9745

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.89755249023438
Linear Weight Rank: 4031
Intra Cos: 0.6042273044586182
Inter Cos: 0.23446467518806458
Norm Quadratic Average: 86.9888916015625
Nearest Class Center Accuracy: 0.997375

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.77845764160156
Linear Weight Rank: 3670
Intra Cos: 0.7176706790924072
Inter Cos: 0.24066530168056488
Norm Quadratic Average: 55.92745590209961
Nearest Class Center Accuracy: 0.9995

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.502746820449829
Linear Weight Rank: 10
Intra Cos: 0.7751820087432861
Inter Cos: 0.2599983811378479
Norm Quadratic Average: 43.290103912353516
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.831338107585907
Inter Cos: 0.3733353316783905
Norm Quadratic Average: 31.06721305847168
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.0877636739909649
Accuracy: 0.979
NC1 Within Class Collapse: 1.8151949644088745
NC2 Equinorm: Features: 0.1029689610004425, Weights: 0.013104824349284172
NC2 Equiangle: Features: 0.24476250542534722, Weights: 0.09750409656100803
NC3 Self-Duality: 0.5607636570930481
NC4 NCC Mismatch: 0.011499999999999955

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: 0.13498850166797638
Inter Cos: 0.15107183158397675
Norm Quadratic Average: 47.7354621887207
Nearest Class Center Accuracy: 0.815

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17057935893535614
Inter Cos: 0.19974929094314575
Norm Quadratic Average: 46.57799530029297
Nearest Class Center Accuracy: 0.802

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17947202920913696
Inter Cos: 0.22032618522644043
Norm Quadratic Average: 61.57765197753906
Nearest Class Center Accuracy: 0.813

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16299974918365479
Inter Cos: 0.21528689563274384
Norm Quadratic Average: 40.507904052734375
Nearest Class Center Accuracy: 0.8455

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1794106513261795
Inter Cos: 0.23897022008895874
Norm Quadratic Average: 40.29775619506836
Nearest Class Center Accuracy: 0.8885

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23338919878005981
Inter Cos: 0.21760016679763794
Norm Quadratic Average: 24.149967193603516
Nearest Class Center Accuracy: 0.9275

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.33465978503227234
Inter Cos: 0.24705086648464203
Norm Quadratic Average: 19.17623519897461
Nearest Class Center Accuracy: 0.953

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.89755249023438
Linear Weight Rank: 4031
Intra Cos: 0.5257583856582642
Inter Cos: 0.268354594707489
Norm Quadratic Average: 83.60053253173828
Nearest Class Center Accuracy: 0.971

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.77845764160156
Linear Weight Rank: 3670
Intra Cos: 0.6298418045043945
Inter Cos: 0.2572157382965088
Norm Quadratic Average: 53.6607666015625
Nearest Class Center Accuracy: 0.974

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.502746820449829
Linear Weight Rank: 10
Intra Cos: 0.6815826296806335
Inter Cos: 0.24233339726924896
Norm Quadratic Average: 41.5594367980957
Nearest Class Center Accuracy: 0.9745

Output Layer:
Intra Cos: 0.7253007888793945
Inter Cos: 0.35094594955444336
Norm Quadratic Average: 29.78329086303711
Nearest Class Center Accuracy: 0.9715

