Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_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: 0.11311887204647064
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: 0.09945102035999298
Inter Cos: 0.1222665086388588
Norm Quadratic Average: 94.94987487792969
Nearest Class Center Accuracy: 0.836

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14337308704853058
Inter Cos: 0.13543181121349335
Norm Quadratic Average: 57.56409454345703
Nearest Class Center Accuracy: 0.856875

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14146612584590912
Inter Cos: 0.12363900244235992
Norm Quadratic Average: 55.972496032714844
Nearest Class Center Accuracy: 0.874125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17094458639621735
Inter Cos: 0.10351421684026718
Norm Quadratic Average: 34.81717300415039
Nearest Class Center Accuracy: 0.908875

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1757080852985382
Inter Cos: 0.08393460512161255
Norm Quadratic Average: 36.19627380371094
Nearest Class Center Accuracy: 0.930125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19445540010929108
Inter Cos: 0.09669426083564758
Norm Quadratic Average: 24.8541316986084
Nearest Class Center Accuracy: 0.9755

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28469178080558777
Inter Cos: 0.09537801146507263
Norm Quadratic Average: 18.968767166137695
Nearest Class Center Accuracy: 0.995875

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.89170837402344
Linear Weight Rank: 4031
Intra Cos: 0.48220670223236084
Inter Cos: 0.11488672345876694
Norm Quadratic Average: 119.54657745361328
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.77613830566406
Linear Weight Rank: 3670
Intra Cos: 0.624126672744751
Inter Cos: 0.14422349631786346
Norm Quadratic Average: 65.03398895263672
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.287144184112549
Linear Weight Rank: 10
Intra Cos: 0.7440338134765625
Inter Cos: 0.1698245108127594
Norm Quadratic Average: 41.4842643737793
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9027531147003174
Inter Cos: 0.26225465536117554
Norm Quadratic Average: 22.549026489257812
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.10011475496739149
Accuracy: 0.974
NC1 Within Class Collapse: 1.6872977018356323
NC2 Equinorm: Features: 0.06500386446714401, Weights: 0.01014713104814291
NC2 Equiangle: Features: 0.20025884840223523, Weights: 0.08978684743245442
NC3 Self-Duality: 0.640619695186615
NC4 NCC Mismatch: 0.007000000000000006

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: 0.12532202899456024
Inter Cos: 0.12795603275299072
Norm Quadratic Average: 93.63102722167969
Nearest Class Center Accuracy: 0.8305

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1563817858695984
Inter Cos: 0.14699403941631317
Norm Quadratic Average: 57.07048797607422
Nearest Class Center Accuracy: 0.8455

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1540265530347824
Inter Cos: 0.12529422342777252
Norm Quadratic Average: 55.53927230834961
Nearest Class Center Accuracy: 0.866

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17228755354881287
Inter Cos: 0.10329828411340714
Norm Quadratic Average: 34.80479049682617
Nearest Class Center Accuracy: 0.8985

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17805951833724976
Inter Cos: 0.08783341199159622
Norm Quadratic Average: 36.226097106933594
Nearest Class Center Accuracy: 0.919

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19279958307743073
Inter Cos: 0.1088971495628357
Norm Quadratic Average: 24.856210708618164
Nearest Class Center Accuracy: 0.9475

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2585749626159668
Inter Cos: 0.0898490622639656
Norm Quadratic Average: 18.82807731628418
Nearest Class Center Accuracy: 0.9695

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.89170837402344
Linear Weight Rank: 4031
Intra Cos: 0.4115181863307953
Inter Cos: 0.1168961450457573
Norm Quadratic Average: 116.63018035888672
Nearest Class Center Accuracy: 0.971

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.77613830566406
Linear Weight Rank: 3670
Intra Cos: 0.5289095640182495
Inter Cos: 0.15384526550769806
Norm Quadratic Average: 63.03739547729492
Nearest Class Center Accuracy: 0.972

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.287144184112549
Linear Weight Rank: 10
Intra Cos: 0.631322979927063
Inter Cos: 0.1835619956254959
Norm Quadratic Average: 40.00779724121094
Nearest Class Center Accuracy: 0.971

Output Layer:
Intra Cos: 0.787965714931488
Inter Cos: 0.2986692190170288
Norm Quadratic Average: 21.601804733276367
Nearest Class Center Accuracy: 0.972

