Model save path: ./New_Models/bn_True_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: 0.026104912161827087
Inter Cos: 0.027863120660185814
Norm Quadratic Average: 8.513383865356445
Nearest Class Center Accuracy: 0.04856

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02251996286213398
Inter Cos: 0.023326177150011063
Norm Quadratic Average: 4.53953742980957
Nearest Class Center Accuracy: 0.06134

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017966391518712044
Inter Cos: 0.017854006960988045
Norm Quadratic Average: 3.358628034591675
Nearest Class Center Accuracy: 0.07026

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023438822478055954
Inter Cos: 0.020108195021748543
Norm Quadratic Average: 2.3029584884643555
Nearest Class Center Accuracy: 0.0803

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02584289386868477
Inter Cos: 0.022721748799085617
Norm Quadratic Average: 1.5322030782699585
Nearest Class Center Accuracy: 0.08854

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08363404124975204
Inter Cos: 0.05591680854558945
Norm Quadratic Average: 1.0641599893569946
Nearest Class Center Accuracy: 0.09952

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5032805800437927
Inter Cos: 0.11842275410890579
Norm Quadratic Average: 1.1056402921676636
Nearest Class Center Accuracy: 0.1

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 4.50662088394165
Linear Weight Rank: 510
Intra Cos: 0.9014231562614441
Inter Cos: 0.26522111892700195
Norm Quadratic Average: 40.97319793701172
Nearest Class Center Accuracy: 0.1

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.733675003051758
Linear Weight Rank: 1582
Intra Cos: 0.938154399394989
Inter Cos: 0.3486204147338867
Norm Quadratic Average: 31.755802154541016
Nearest Class Center Accuracy: 0.1

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 4.82220458984375
Linear Weight Rank: 97
Intra Cos: 0.9401534199714661
Inter Cos: 0.34679660201072693
Norm Quadratic Average: 29.33773422241211
Nearest Class Center Accuracy: 0.1

Output Layer:
Intra Cos: 0.9466922283172607
Inter Cos: 0.4148484766483307
Norm Quadratic Average: 29.77669906616211
Nearest Class Center Accuracy: 0.1

Test Set:
Average Loss: 1.7393923740386963
Accuracy: 0.5859
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.237868532538414, Weights: 0.015467067249119282
NC2 Equiangle: Features: 0.19342599579782196, Weights: 0.14320208925189393
NC3 Self-Duality: 0.24924403429031372
NC4 NCC Mismatch: 0.15659999999999996

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: 0.012022391892969608
Inter Cos: 0.24363058805465698
Norm Quadratic Average: 8.573514938354492
Nearest Class Center Accuracy: 0.2633

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01590803638100624
Inter Cos: 0.20618213713169098
Norm Quadratic Average: 4.574028491973877
Nearest Class Center Accuracy: 0.3968

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013391763903200626
Inter Cos: 0.1445533186197281
Norm Quadratic Average: 3.374558210372925
Nearest Class Center Accuracy: 0.5138

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013160665519535542
Inter Cos: 0.14231976866722107
Norm Quadratic Average: 2.308816909790039
Nearest Class Center Accuracy: 0.6226

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.011011186055839062
Inter Cos: 0.12244874238967896
Norm Quadratic Average: 1.52306067943573
Nearest Class Center Accuracy: 0.694

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020136065781116486
Inter Cos: 0.19742965698242188
Norm Quadratic Average: 1.0271034240722656
Nearest Class Center Accuracy: 0.673

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0688939169049263
Inter Cos: 0.4375675916671753
Norm Quadratic Average: 0.9357123374938965
Nearest Class Center Accuracy: 0.6093

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 4.50662088394165
Linear Weight Rank: 510
Intra Cos: 0.22280314564704895
Inter Cos: 0.5266944169998169
Norm Quadratic Average: 31.113880157470703
Nearest Class Center Accuracy: 0.588

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.733675003051758
Linear Weight Rank: 1582
Intra Cos: 0.2485341876745224
Inter Cos: 0.5572890639305115
Norm Quadratic Average: 24.317441940307617
Nearest Class Center Accuracy: 0.5852

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 4.82220458984375
Linear Weight Rank: 97
Intra Cos: 0.24009479582309723
Inter Cos: 0.557813286781311
Norm Quadratic Average: 22.80079460144043
Nearest Class Center Accuracy: 0.5829

Output Layer:
Intra Cos: 0.24759288132190704
Inter Cos: 0.5795748233795166
Norm Quadratic Average: 23.01323699951172
Nearest Class Center Accuracy: 0.5821

