Model save path: ./New_Models/bn_False_dataset_CIFAR100_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022893192246556282
Inter Cos: 0.07011394202709198
Norm Quadratic Average: 29.326322555541992
Nearest Class Center Accuracy: 0.03258

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.042982570827007294
Inter Cos: 0.07764604687690735
Norm Quadratic Average: 40.30786895751953
Nearest Class Center Accuracy: 0.0419

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.04835507273674011
Inter Cos: 0.08423953503370285
Norm Quadratic Average: 56.09717559814453
Nearest Class Center Accuracy: 0.0463

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.04282642900943756
Inter Cos: 0.04540214687585831
Norm Quadratic Average: 102.52336883544922
Nearest Class Center Accuracy: 0.05318

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.042342979460954666
Inter Cos: 0.04398190230131149
Norm Quadratic Average: 71.64286804199219
Nearest Class Center Accuracy: 0.06328

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.04105684533715248
Inter Cos: 0.038835640996694565
Norm Quadratic Average: 30.475927352905273
Nearest Class Center Accuracy: 0.07068

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10037557035684586
Inter Cos: 0.07614660263061523
Norm Quadratic Average: 7.041571617126465
Nearest Class Center Accuracy: 0.07844

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.48193618655204773
Inter Cos: 0.33591359853744507
Norm Quadratic Average: 2.6570286750793457
Nearest Class Center Accuracy: 0.09682

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 5.112133979797363
Linear Weight Rank: 1600
Intra Cos: 0.6930493116378784
Inter Cos: 0.39222320914268494
Norm Quadratic Average: 22.80715560913086
Nearest Class Center Accuracy: 0.09956

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 5.40781831741333
Linear Weight Rank: 3100
Intra Cos: 0.7408749461174011
Inter Cos: 0.41357582807540894
Norm Quadratic Average: 32.91286087036133
Nearest Class Center Accuracy: 0.09996

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 5.56732702255249
Linear Weight Rank: 97
Intra Cos: 0.7336603999137878
Inter Cos: 0.3951234817504883
Norm Quadratic Average: 43.29907989501953
Nearest Class Center Accuracy: 0.1

Output Layer:
Intra Cos: 0.7680529356002808
Inter Cos: 0.4325574040412903
Norm Quadratic Average: 61.90974807739258
Nearest Class Center Accuracy: 0.1

Test Set:
Average Loss: 3.4860818214416502
Accuracy: 0.4261
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.2626223564147949, Weights: 0.042900338768959045
NC2 Equiangle: Features: 0.2667831636679293, Weights: 0.17771398062657828
NC3 Self-Duality: 0.398619145154953
NC4 NCC Mismatch: 0.29510000000000003

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.006621268577873707
Inter Cos: 0.4067547917366028
Norm Quadratic Average: 29.42218780517578
Nearest Class Center Accuracy: 0.1136

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.015605027787387371
Inter Cos: 0.30795416235923767
Norm Quadratic Average: 40.48387908935547
Nearest Class Center Accuracy: 0.1862

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02180267497897148
Inter Cos: 0.36332499980926514
Norm Quadratic Average: 56.34455871582031
Nearest Class Center Accuracy: 0.227

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02109616994857788
Inter Cos: 0.41723185777664185
Norm Quadratic Average: 103.09908294677734
Nearest Class Center Accuracy: 0.2631

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025600001215934753
Inter Cos: 0.3213721215724945
Norm Quadratic Average: 72.21693420410156
Nearest Class Center Accuracy: 0.3576

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.026338744908571243
Inter Cos: 0.22634468972682953
Norm Quadratic Average: 30.689586639404297
Nearest Class Center Accuracy: 0.4476

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.040626104921102524
Inter Cos: 0.37858644127845764
Norm Quadratic Average: 7.058526515960693
Nearest Class Center Accuracy: 0.4488

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10891003161668777
Inter Cos: 0.5878291726112366
Norm Quadratic Average: 2.594024419784546
Nearest Class Center Accuracy: 0.4085

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 5.112133979797363
Linear Weight Rank: 1600
Intra Cos: 0.1251855045557022
Inter Cos: 0.6524171829223633
Norm Quadratic Average: 21.890222549438477
Nearest Class Center Accuracy: 0.4146

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 5.40781831741333
Linear Weight Rank: 3100
Intra Cos: 0.1346411556005478
Inter Cos: 0.6740853786468506
Norm Quadratic Average: 31.448450088500977
Nearest Class Center Accuracy: 0.4264

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 5.56732702255249
Linear Weight Rank: 97
Intra Cos: 0.14602795243263245
Inter Cos: 0.6607051491737366
Norm Quadratic Average: 41.561283111572266
Nearest Class Center Accuracy: 0.4277

Output Layer:
Intra Cos: 0.14302699267864227
Inter Cos: 0.7087767124176025
Norm Quadratic Average: 59.328460693359375
Nearest Class Center Accuracy: 0.424

