Model save path: ./New_Models/bn_True_dataset_CIFAR100_epochs_200_lr_0.01_model_type_vgg19_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.005.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022893190383911133
Inter Cos: 0.07011394202709198
Norm Quadratic Average: 29.326326370239258
Nearest Class Center Accuracy: 0.03258

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01329636387526989
Inter Cos: 0.02945215441286564
Norm Quadratic Average: 10.113828659057617
Nearest Class Center Accuracy: 0.03872

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018023822456598282
Inter Cos: 0.03836512938141823
Norm Quadratic Average: 7.321662902832031
Nearest Class Center Accuracy: 0.05714

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013054641894996166
Inter Cos: 0.029458709061145782
Norm Quadratic Average: 5.503669261932373
Nearest Class Center Accuracy: 0.06432

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020274877548217773
Inter Cos: 0.018658269196748734
Norm Quadratic Average: 4.056053638458252
Nearest Class Center Accuracy: 0.07226

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.021046821027994156
Inter Cos: 0.019121039658784866
Norm Quadratic Average: 3.0645596981048584
Nearest Class Center Accuracy: 0.0759

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023192517459392548
Inter Cos: 0.02050146274268627
Norm Quadratic Average: 2.9051713943481445
Nearest Class Center Accuracy: 0.07796

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.021799415349960327
Inter Cos: 0.018792524933815002
Norm Quadratic Average: 2.881999969482422
Nearest Class Center Accuracy: 0.08012

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.032926492393016815
Inter Cos: 0.027022896334528923
Norm Quadratic Average: 2.130711793899536
Nearest Class Center Accuracy: 0.08706

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03978315368294716
Inter Cos: 0.030854811891913414
Norm Quadratic Average: 1.393791913986206
Nearest Class Center Accuracy: 0.09214

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.07023148983716965
Inter Cos: 0.04441726207733154
Norm Quadratic Average: 1.0802881717681885
Nearest Class Center Accuracy: 0.09622

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17121513187885284
Inter Cos: 0.06677117943763733
Norm Quadratic Average: 0.9087827205657959
Nearest Class Center Accuracy: 0.09752

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4725690186023712
Inter Cos: 0.14077109098434448
Norm Quadratic Average: 0.7428101301193237
Nearest Class Center Accuracy: 0.09866

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8269590735435486
Inter Cos: 0.266208291053772
Norm Quadratic Average: 0.5417098999023438
Nearest Class Center Accuracy: 0.09998

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9091602563858032
Inter Cos: 0.31561896204948425
Norm Quadratic Average: 0.5851991772651672
Nearest Class Center Accuracy: 0.1

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9597368836402893
Inter Cos: 0.3350365161895752
Norm Quadratic Average: 1.1881306171417236
Nearest Class Center Accuracy: 0.1

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.9366581439971924
Linear Weight Rank: 346
Intra Cos: 0.9784600138664246
Inter Cos: 0.3561246395111084
Norm Quadratic Average: 39.13808059692383
Nearest Class Center Accuracy: 0.1

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.052541732788086
Linear Weight Rank: 1782
Intra Cos: 0.981505274772644
Inter Cos: 0.40351149439811707
Norm Quadratic Average: 33.889015197753906
Nearest Class Center Accuracy: 0.1

Layer 18: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 4.1735639572143555
Linear Weight Rank: 97
Intra Cos: 0.9812586903572083
Inter Cos: 0.4230901598930359
Norm Quadratic Average: 31.608903884887695
Nearest Class Center Accuracy: 0.1

Output Layer:
Intra Cos: 0.9824634790420532
Inter Cos: 0.4431595802307129
Norm Quadratic Average: 32.465579986572266
Nearest Class Center Accuracy: 0.1

Test Set:
Average Loss: 1.8788851890563965
Accuracy: 0.6264
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.14696799218654633, Weights: 0.01749403588473797
NC2 Equiangle: Features: 0.22106045809659092, Weights: 0.17804598721590909
NC3 Self-Duality: 0.15251122415065765
NC4 NCC Mismatch: 0.059699999999999975

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: 29.422189712524414
Nearest Class Center Accuracy: 0.1136

Layer 1: Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0077008893713355064
Inter Cos: 0.19930769503116608
Norm Quadratic Average: 10.177380561828613
Nearest Class Center Accuracy: 0.2177

Layer 2: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.010252534411847591
Inter Cos: 0.2623884379863739
Norm Quadratic Average: 7.369772434234619
Nearest Class Center Accuracy: 0.36

Layer 3: Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.00981099996715784
Inter Cos: 0.14863525331020355
Norm Quadratic Average: 5.52855920791626
Nearest Class Center Accuracy: 0.4904

Layer 4: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.014283831231296062
Inter Cos: 0.1828538328409195
Norm Quadratic Average: 4.072944641113281
Nearest Class Center Accuracy: 0.5471

Layer 5: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.015292196534574032
Inter Cos: 0.16166484355926514
Norm Quadratic Average: 3.0746657848358154
Nearest Class Center Accuracy: 0.5854

Layer 6: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.015664242208003998
Inter Cos: 0.13948029279708862
Norm Quadratic Average: 2.9100265502929688
Nearest Class Center Accuracy: 0.6024

Layer 7: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013138952665030956
Inter Cos: 0.11665688455104828
Norm Quadratic Average: 2.881389856338501
Nearest Class Center Accuracy: 0.6276

Layer 8: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01563248038291931
Inter Cos: 0.1522430181503296
Norm Quadratic Average: 2.1255104541778564
Nearest Class Center Accuracy: 0.6614

Layer 9: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01572604477405548
Inter Cos: 0.14360849559307098
Norm Quadratic Average: 1.3751106262207031
Nearest Class Center Accuracy: 0.6897

Layer 10: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02179095149040222
Inter Cos: 0.180607870221138
Norm Quadratic Average: 1.0335259437561035
Nearest Class Center Accuracy: 0.6704

Layer 11: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03958596661686897
Inter Cos: 0.2646969258785248
Norm Quadratic Average: 0.8212125897407532
Nearest Class Center Accuracy: 0.6175

Layer 12: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17971396446228027
Inter Cos: 0.38136088848114014
Norm Quadratic Average: 0.6209378838539124
Nearest Class Center Accuracy: 0.5545

Layer 13: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2782041132450104
Inter Cos: 0.40500763058662415
Norm Quadratic Average: 0.4323144853115082
Nearest Class Center Accuracy: 0.5891

Layer 14: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2879316806793213
Inter Cos: 0.4405082166194916
Norm Quadratic Average: 0.48760053515434265
Nearest Class Center Accuracy: 0.6282

Layer 15: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.29355207085609436
Inter Cos: 0.5059700012207031
Norm Quadratic Average: 1.0636038780212402
Nearest Class Center Accuracy: 0.633

Layer 16: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.9366581439971924
Linear Weight Rank: 346
Intra Cos: 0.3031124174594879
Inter Cos: 0.5667315721511841
Norm Quadratic Average: 35.6413688659668
Nearest Class Center Accuracy: 0.6333

Layer 17: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 4.052541732788086
Linear Weight Rank: 1782
Intra Cos: 0.30914783477783203
Inter Cos: 0.5982016921043396
Norm Quadratic Average: 31.22906494140625
Nearest Class Center Accuracy: 0.6329

Layer 18: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 4.1735639572143555
Linear Weight Rank: 97
Intra Cos: 0.3076573312282562
Inter Cos: 0.6175134181976318
Norm Quadratic Average: 29.498008728027344
Nearest Class Center Accuracy: 0.631

Output Layer:
Intra Cos: 0.3103567957878113
Inter Cos: 0.6547812223434448
Norm Quadratic Average: 30.472131729125977
Nearest Class Center Accuracy: 0.6301

