Model save path: ./New_Models/bn_False_dataset_CIFAR100_epochs_200_lr_0.01_model_type_vgg11_rand_seed_265358_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: 29.326324462890625
Nearest Class Center Accuracy: 0.03258

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.041150618344545364
Inter Cos: 0.07498040050268173
Norm Quadratic Average: 38.5867919921875
Nearest Class Center Accuracy: 0.04274

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.04522373154759407
Inter Cos: 0.07585222274065018
Norm Quadratic Average: 51.71250534057617
Nearest Class Center Accuracy: 0.04746

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.04153518006205559
Inter Cos: 0.04597525671124458
Norm Quadratic Average: 90.11688995361328
Nearest Class Center Accuracy: 0.05472

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.039215605705976486
Inter Cos: 0.04000367596745491
Norm Quadratic Average: 53.46961212158203
Nearest Class Center Accuracy: 0.06412

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.041109196841716766
Inter Cos: 0.03882664814591408
Norm Quadratic Average: 20.34825325012207
Nearest Class Center Accuracy: 0.0724

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.12354292720556259
Inter Cos: 0.09652943164110184
Norm Quadratic Average: 4.969966888427734
Nearest Class Center Accuracy: 0.07954

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5480178594589233
Inter Cos: 0.40455448627471924
Norm Quadratic Average: 2.172555446624756
Nearest Class Center Accuracy: 0.09704

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 5.1296000480651855
Linear Weight Rank: 1755
Intra Cos: 0.7251047492027283
Inter Cos: 0.5223349928855896
Norm Quadratic Average: 20.862140655517578
Nearest Class Center Accuracy: 0.09952

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 5.424717426300049
Linear Weight Rank: 3091
Intra Cos: 0.7725808620452881
Inter Cos: 0.545352041721344
Norm Quadratic Average: 32.36272048950195
Nearest Class Center Accuracy: 0.09996

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 5.593395233154297
Linear Weight Rank: 97
Intra Cos: 0.7769830822944641
Inter Cos: 0.5111764073371887
Norm Quadratic Average: 43.792396545410156
Nearest Class Center Accuracy: 0.1

Output Layer:
Intra Cos: 0.8236750364303589
Inter Cos: 0.5469987392425537
Norm Quadratic Average: 63.95808410644531
Nearest Class Center Accuracy: 0.1

Test Set:
Average Loss: 3.5598764167785646
Accuracy: 0.4305
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.2594524025917053, Weights: 0.04629667475819588
NC2 Equiangle: Features: 0.27711657591540406, Weights: 0.1769089207504735
NC3 Self-Duality: 0.4093707501888275
NC4 NCC Mismatch: 0.30489999999999995

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.006621266715228558
Inter Cos: 0.4067547917366028
Norm Quadratic Average: 29.42218589782715
Nearest Class Center Accuracy: 0.1136

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.014884666539728642
Inter Cos: 0.3035597801208496
Norm Quadratic Average: 38.764102935791016
Nearest Class Center Accuracy: 0.194

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020650357007980347
Inter Cos: 0.36554449796676636
Norm Quadratic Average: 51.962303161621094
Nearest Class Center Accuracy: 0.239

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02043086290359497
Inter Cos: 0.40516674518585205
Norm Quadratic Average: 90.65164947509766
Nearest Class Center Accuracy: 0.2805

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023520827293395996
Inter Cos: 0.3011326193809509
Norm Quadratic Average: 53.939762115478516
Nearest Class Center Accuracy: 0.3801

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02695450559258461
Inter Cos: 0.22178049385547638
Norm Quadratic Average: 20.491708755493164
Nearest Class Center Accuracy: 0.4747

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.05281371250748634
Inter Cos: 0.40085655450820923
Norm Quadratic Average: 4.9772047996521
Nearest Class Center Accuracy: 0.4593

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10032673180103302
Inter Cos: 0.6417422890663147
Norm Quadratic Average: 2.1115903854370117
Nearest Class Center Accuracy: 0.4183

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 5.1296000480651855
Linear Weight Rank: 1755
Intra Cos: 0.13558894395828247
Inter Cos: 0.697140634059906
Norm Quadratic Average: 19.973777770996094
Nearest Class Center Accuracy: 0.4216

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 5.424717426300049
Linear Weight Rank: 3091
Intra Cos: 0.1491672545671463
Inter Cos: 0.6964573264122009
Norm Quadratic Average: 30.86492919921875
Nearest Class Center Accuracy: 0.4261

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 5.593395233154297
Linear Weight Rank: 97
Intra Cos: 0.16497685015201569
Inter Cos: 0.6659322381019592
Norm Quadratic Average: 41.99310302734375
Nearest Class Center Accuracy: 0.4277

Output Layer:
Intra Cos: 0.15704019367694855
Inter Cos: 0.6974632143974304
Norm Quadratic Average: 61.18955612182617
Nearest Class Center Accuracy: 0.4241

