Model save path: ./New_Models/bn_False_dataset_CIFAR10_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.0005.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.021450398489832878
Inter Cos: 0.11371058225631714
Norm Quadratic Average: 27.691619873046875
Nearest Class Center Accuracy: 0.279125

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.024574223905801773
Inter Cos: 0.0957556962966919
Norm Quadratic Average: 32.579769134521484
Nearest Class Center Accuracy: 0.303375

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.031246129423379898
Inter Cos: 0.10113828629255295
Norm Quadratic Average: 25.24641227722168
Nearest Class Center Accuracy: 0.37125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.034959979355335236
Inter Cos: 0.09753647446632385
Norm Quadratic Average: 30.700929641723633
Nearest Class Center Accuracy: 0.413125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.05214904993772507
Inter Cos: 0.1217297688126564
Norm Quadratic Average: 19.63128662109375
Nearest Class Center Accuracy: 0.44

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06156741827726364
Inter Cos: 0.1197984591126442
Norm Quadratic Average: 18.04523277282715
Nearest Class Center Accuracy: 0.467375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08140140771865845
Inter Cos: 0.13422049582004547
Norm Quadratic Average: 9.934818267822266
Nearest Class Center Accuracy: 0.519

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11100497841835022
Inter Cos: 0.15463854372501373
Norm Quadratic Average: 7.348093509674072
Nearest Class Center Accuracy: 0.69525

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.01077270507812
Linear Weight Rank: 4031
Intra Cos: 0.3107518255710602
Inter Cos: 0.2878342568874359
Norm Quadratic Average: 29.58597755432129
Nearest Class Center Accuracy: 0.96675

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.07034683227539
Linear Weight Rank: 3671
Intra Cos: 0.5909725427627563
Inter Cos: 0.4443446397781372
Norm Quadratic Average: 25.844770431518555
Nearest Class Center Accuracy: 0.998375

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.2487053871154785
Linear Weight Rank: 10
Intra Cos: 0.7349766492843628
Inter Cos: 0.5520697832107544
Norm Quadratic Average: 30.2731990814209
Nearest Class Center Accuracy: 0.9995

Output Layer:
Intra Cos: 0.8421099185943604
Inter Cos: 0.7114052772521973
Norm Quadratic Average: 37.36693572998047
Nearest Class Center Accuracy: 0.99825

Test Set:
Average Loss: 3.2839022369384767
Accuracy: 0.5875
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.24368160963058472, Weights: 0.04611334204673767
NC2 Equiangle: Features: 0.4569803449842665, Weights: 0.16205790837605794
NC3 Self-Duality: 0.46392425894737244
NC4 NCC Mismatch: 0.15100000000000002

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018480457365512848
Inter Cos: 0.09352367371320724
Norm Quadratic Average: 27.530664443969727
Nearest Class Center Accuracy: 0.2895

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025748256593942642
Inter Cos: 0.07881596684455872
Norm Quadratic Average: 32.365753173828125
Nearest Class Center Accuracy: 0.3215

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03241221606731415
Inter Cos: 0.09179987013339996
Norm Quadratic Average: 25.128395080566406
Nearest Class Center Accuracy: 0.3865

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.034578584134578705
Inter Cos: 0.08888386934995651
Norm Quadratic Average: 30.621597290039062
Nearest Class Center Accuracy: 0.437

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.04774865135550499
Inter Cos: 0.11204367876052856
Norm Quadratic Average: 19.600582122802734
Nearest Class Center Accuracy: 0.4545

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.05566785857081413
Inter Cos: 0.11009424924850464
Norm Quadratic Average: 18.036766052246094
Nearest Class Center Accuracy: 0.4685

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06598074734210968
Inter Cos: 0.12980735301971436
Norm Quadratic Average: 9.915363311767578
Nearest Class Center Accuracy: 0.4745

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.07490287721157074
Inter Cos: 0.14426463842391968
Norm Quadratic Average: 7.297013759613037
Nearest Class Center Accuracy: 0.5245

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.01077270507812
Linear Weight Rank: 4031
Intra Cos: 0.13470792770385742
Inter Cos: 0.25499051809310913
Norm Quadratic Average: 28.474485397338867
Nearest Class Center Accuracy: 0.572

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.07034683227539
Linear Weight Rank: 3671
Intra Cos: 0.21273960173130035
Inter Cos: 0.3817174434661865
Norm Quadratic Average: 24.077741622924805
Nearest Class Center Accuracy: 0.58

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.2487053871154785
Linear Weight Rank: 10
Intra Cos: 0.24897506833076477
Inter Cos: 0.46610227227211
Norm Quadratic Average: 27.963573455810547
Nearest Class Center Accuracy: 0.561

Output Layer:
Intra Cos: 0.2870613634586334
Inter Cos: 0.5736121535301208
Norm Quadratic Average: 34.34657669067383
Nearest Class Center Accuracy: 0.5275

