Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_265358_test_samples_None_train_samples_None_weight_decay_0.005.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116753190755844
Inter Cos: 0.10967151820659637
Norm Quadratic Average: 23.567670822143555
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09887123107910156
Inter Cos: 0.1027190312743187
Norm Quadratic Average: 2.8662149906158447
Nearest Class Center Accuracy: 0.85475

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18345466256141663
Inter Cos: 0.13446256518363953
Norm Quadratic Average: 1.4875149726867676
Nearest Class Center Accuracy: 0.9138

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.22332459688186646
Inter Cos: 0.15277427434921265
Norm Quadratic Average: 0.9382871389389038
Nearest Class Center Accuracy: 0.9520666666666666

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3138810992240906
Inter Cos: 0.15676037967205048
Norm Quadratic Average: 0.4767545163631439
Nearest Class Center Accuracy: 0.9899666666666667

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6173155307769775
Inter Cos: 0.24884210526943207
Norm Quadratic Average: 0.4010535776615143
Nearest Class Center Accuracy: 0.9998833333333333

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8254287242889404
Inter Cos: 0.21608829498291016
Norm Quadratic Average: 0.6004404425621033
Nearest Class Center Accuracy: 1.0

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9775292873382568
Inter Cos: 0.14596745371818542
Norm Quadratic Average: 0.9940233826637268
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.1326541900634766
Linear Weight Rank: 10
Intra Cos: 0.9960411190986633
Inter Cos: 0.2068091332912445
Norm Quadratic Average: 23.869596481323242
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.1345276832580566
Linear Weight Rank: 1356
Intra Cos: 0.9974415898323059
Inter Cos: 0.21664753556251526
Norm Quadratic Average: 17.05793571472168
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.134660482406616
Linear Weight Rank: 9
Intra Cos: 0.9979649186134338
Inter Cos: 0.17844732105731964
Norm Quadratic Average: 12.457571983337402
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9983346462249756
Inter Cos: 0.18923461437225342
Norm Quadratic Average: 9.75841236114502
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.015542999303340911
Accuracy: 0.9956
NC1 Within Class Collapse: 0.11948768049478531
NC2 Equinorm: Features: 0.022595826536417007, Weights: 0.010530494153499603
NC2 Equiangle: Features: 0.15024923748440214, Weights: 0.12494512134128147
NC3 Self-Duality: 0.03351280838251114
NC4 NCC Mismatch: 0.00029999999999996696

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219583660364151
Inter Cos: 0.12048852443695068
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1089794933795929
Inter Cos: 0.10306407511234283
Norm Quadratic Average: 2.849480628967285
Nearest Class Center Accuracy: 0.8678

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19532153010368347
Inter Cos: 0.13172031939029694
Norm Quadratic Average: 1.4799562692642212
Nearest Class Center Accuracy: 0.9223

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2376258671283722
Inter Cos: 0.14908042550086975
Norm Quadratic Average: 0.9354070425033569
Nearest Class Center Accuracy: 0.9562

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3251856863498688
Inter Cos: 0.1661590337753296
Norm Quadratic Average: 0.47523877024650574
Nearest Class Center Accuracy: 0.9866

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6216647028923035
Inter Cos: 0.26262590289115906
Norm Quadratic Average: 0.40001171827316284
Nearest Class Center Accuracy: 0.9942

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8180885314941406
Inter Cos: 0.2250421941280365
Norm Quadratic Average: 0.5987739562988281
Nearest Class Center Accuracy: 0.9955

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.9675495624542236
Inter Cos: 0.15734022855758667
Norm Quadratic Average: 0.989357590675354
Nearest Class Center Accuracy: 0.9957

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 2.1326541900634766
Linear Weight Rank: 10
Intra Cos: 0.9818763732910156
Inter Cos: 0.2083047479391098
Norm Quadratic Average: 23.747495651245117
Nearest Class Center Accuracy: 0.9957

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 2.1345276832580566
Linear Weight Rank: 1356
Intra Cos: 0.983569324016571
Inter Cos: 0.21719880402088165
Norm Quadratic Average: 16.970521926879883
Nearest Class Center Accuracy: 0.9955

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.134660482406616
Linear Weight Rank: 9
Intra Cos: 0.9836220741271973
Inter Cos: 0.1796419471502304
Norm Quadratic Average: 12.393030166625977
Nearest Class Center Accuracy: 0.9957

Output Layer:
Intra Cos: 0.9847946763038635
Inter Cos: 0.18236541748046875
Norm Quadratic Average: 9.706564903259277
Nearest Class Center Accuracy: 0.9956

