Model save path: ./New_Models/bn_True_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.03.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0198909230530262
Inter Cos: 0.10477276891469955
Norm Quadratic Average: 27.59718894958496
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02279467135667801
Inter Cos: 0.09578908979892731
Norm Quadratic Average: 2.6398062705993652
Nearest Class Center Accuracy: 0.3969

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02197159081697464
Inter Cos: 0.06472102552652359
Norm Quadratic Average: 1.27965247631073
Nearest Class Center Accuracy: 0.5184

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.019547024741768837
Inter Cos: 0.05599493533372879
Norm Quadratic Average: 0.9701223969459534
Nearest Class Center Accuracy: 0.6109

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.031158767640590668
Inter Cos: 0.05944539234042168
Norm Quadratic Average: 0.6912490725517273
Nearest Class Center Accuracy: 0.73798

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.05114045739173889
Inter Cos: 0.07036814093589783
Norm Quadratic Average: 0.6087446212768555
Nearest Class Center Accuracy: 0.839

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20901210606098175
Inter Cos: 0.22028428316116333
Norm Quadratic Average: 0.38420939445495605
Nearest Class Center Accuracy: 0.9584

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.809970498085022
Inter Cos: 0.290448397397995
Norm Quadratic Average: 0.4552918076515198
Nearest Class Center Accuracy: 0.99996

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.000546932220459
Linear Weight Rank: 9
Intra Cos: 0.9776756167411804
Inter Cos: 0.2164224535226822
Norm Quadratic Average: 22.63526153564453
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0030107498168945
Linear Weight Rank: 1605
Intra Cos: 0.9843308925628662
Inter Cos: 0.2265055775642395
Norm Quadratic Average: 14.946996688842773
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0030078887939453
Linear Weight Rank: 9
Intra Cos: 0.9872320890426636
Inter Cos: 0.21021197736263275
Norm Quadratic Average: 10.079780578613281
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9900389909744263
Inter Cos: 0.17781224846839905
Norm Quadratic Average: 7.248444080352783
Nearest Class Center Accuracy: 0.99998

Test Set:
Average Loss: 0.5063401575088501
Accuracy: 0.8452
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.11777762323617935, Weights: 0.007577382959425449
NC2 Equiangle: Features: 0.15914251539442276, Weights: 0.10463015238444011
NC3 Self-Duality: 0.055745046585798264
NC4 NCC Mismatch: 0.017900000000000027

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018526077270507812
Inter Cos: 0.1042705774307251
Norm Quadratic Average: 27.550140380859375
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02083381451666355
Inter Cos: 0.09757167100906372
Norm Quadratic Average: 2.6376490592956543
Nearest Class Center Accuracy: 0.4122

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02063090167939663
Inter Cos: 0.06621666252613068
Norm Quadratic Average: 1.2802320718765259
Nearest Class Center Accuracy: 0.5321

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018233658745884895
Inter Cos: 0.05685222148895264
Norm Quadratic Average: 0.9712877869606018
Nearest Class Center Accuracy: 0.6116

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.026645267382264137
Inter Cos: 0.06047552451491356
Norm Quadratic Average: 0.6915766596794128
Nearest Class Center Accuracy: 0.7048

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.04019109532237053
Inter Cos: 0.07234640419483185
Norm Quadratic Average: 0.6066522598266602
Nearest Class Center Accuracy: 0.7593

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15107013285160065
Inter Cos: 0.22113917768001556
Norm Quadratic Average: 0.37939196825027466
Nearest Class Center Accuracy: 0.8033

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4375198483467102
Inter Cos: 0.32653626799583435
Norm Quadratic Average: 0.42385461926460266
Nearest Class Center Accuracy: 0.8435

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.000546932220459
Linear Weight Rank: 9
Intra Cos: 0.5259367823600769
Inter Cos: 0.32211387157440186
Norm Quadratic Average: 20.245635986328125
Nearest Class Center Accuracy: 0.8443

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.0030107498168945
Linear Weight Rank: 1605
Intra Cos: 0.5377365946769714
Inter Cos: 0.3356134295463562
Norm Quadratic Average: 13.371872901916504
Nearest Class Center Accuracy: 0.8448

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0030078887939453
Linear Weight Rank: 9
Intra Cos: 0.5454270839691162
Inter Cos: 0.33617720007896423
Norm Quadratic Average: 9.011500358581543
Nearest Class Center Accuracy: 0.8457

Output Layer:
Intra Cos: 0.5699895024299622
Inter Cos: 0.32798758149147034
Norm Quadratic Average: 6.491095066070557
Nearest Class Center Accuracy: 0.8458

