Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946067094802856
Inter Cos: 0.11311887204647064
Norm Quadratic Average: 23.53293800354004
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11127924174070358
Inter Cos: 0.12890402972698212
Norm Quadratic Average: 45.96346664428711
Nearest Class Center Accuracy: 0.8235

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15708735585212708
Inter Cos: 0.16303114593029022
Norm Quadratic Average: 43.254486083984375
Nearest Class Center Accuracy: 0.816625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17786100506782532
Inter Cos: 0.17837905883789062
Norm Quadratic Average: 56.17287063598633
Nearest Class Center Accuracy: 0.831625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1961454451084137
Inter Cos: 0.1786811202764511
Norm Quadratic Average: 37.70671081542969
Nearest Class Center Accuracy: 0.8665

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2230575680732727
Inter Cos: 0.19640479981899261
Norm Quadratic Average: 36.6495475769043
Nearest Class Center Accuracy: 0.91125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.288741797208786
Inter Cos: 0.17434650659561157
Norm Quadratic Average: 22.352018356323242
Nearest Class Center Accuracy: 0.950625

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4118187427520752
Inter Cos: 0.2248476892709732
Norm Quadratic Average: 17.794504165649414
Nearest Class Center Accuracy: 0.9825

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.9375228881836
Linear Weight Rank: 4031
Intra Cos: 0.6388252973556519
Inter Cos: 0.27109459042549133
Norm Quadratic Average: 79.43386840820312
Nearest Class Center Accuracy: 0.99825

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.40389633178711
Linear Weight Rank: 3671
Intra Cos: 0.730902910232544
Inter Cos: 0.2737624943256378
Norm Quadratic Average: 51.59484100341797
Nearest Class Center Accuracy: 0.9995

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.49609637260437
Linear Weight Rank: 10
Intra Cos: 0.771414577960968
Inter Cos: 0.2667427062988281
Norm Quadratic Average: 40.123687744140625
Nearest Class Center Accuracy: 0.999625

Output Layer:
Intra Cos: 0.8038283586502075
Inter Cos: 0.32735109329223633
Norm Quadratic Average: 29.100629806518555
Nearest Class Center Accuracy: 0.999875

Test Set:
Average Loss: 0.08807924057543277
Accuracy: 0.9795
NC1 Within Class Collapse: 1.6918833255767822
NC2 Equinorm: Features: 0.11348740756511688, Weights: 0.011841099709272385
NC2 Equiangle: Features: 0.24946585761176215, Weights: 0.0980974833170573
NC3 Self-Duality: 0.555599570274353
NC4 NCC Mismatch: 0.01100000000000001

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133805871009827
Inter Cos: 0.11957792192697525
Norm Quadratic Average: 22.82430076599121
Nearest Class Center Accuracy: 0.809

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13226337730884552
Inter Cos: 0.14562955498695374
Norm Quadratic Average: 45.10007858276367
Nearest Class Center Accuracy: 0.816

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1705859750509262
Inter Cos: 0.19975720345973969
Norm Quadratic Average: 42.50352478027344
Nearest Class Center Accuracy: 0.818

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1758187711238861
Inter Cos: 0.21585337817668915
Norm Quadratic Average: 55.19240188598633
Nearest Class Center Accuracy: 0.8295

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17739208042621613
Inter Cos: 0.2089693397283554
Norm Quadratic Average: 37.021907806396484
Nearest Class Center Accuracy: 0.8585

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2025902271270752
Inter Cos: 0.22536128759384155
Norm Quadratic Average: 36.053466796875
Nearest Class Center Accuracy: 0.8975

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2623104751110077
Inter Cos: 0.18612003326416016
Norm Quadratic Average: 21.938627243041992
Nearest Class Center Accuracy: 0.937

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3662172555923462
Inter Cos: 0.21574899554252625
Norm Quadratic Average: 17.403148651123047
Nearest Class Center Accuracy: 0.959

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.9375228881836
Linear Weight Rank: 4031
Intra Cos: 0.5745897889137268
Inter Cos: 0.24415096640586853
Norm Quadratic Average: 77.18150329589844
Nearest Class Center Accuracy: 0.9735

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.40389633178711
Linear Weight Rank: 3671
Intra Cos: 0.6603258848190308
Inter Cos: 0.24775545299053192
Norm Quadratic Average: 50.03030014038086
Nearest Class Center Accuracy: 0.977

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.49609637260437
Linear Weight Rank: 10
Intra Cos: 0.6953523755073547
Inter Cos: 0.26439350843429565
Norm Quadratic Average: 38.948307037353516
Nearest Class Center Accuracy: 0.977

Output Layer:
Intra Cos: 0.7177939414978027
Inter Cos: 0.3636838495731354
Norm Quadratic Average: 28.237424850463867
Nearest Class Center Accuracy: 0.9755

