Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_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: 0.08946065604686737
Inter Cos: 0.11311887204647064
Norm Quadratic Average: 23.532936096191406
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10101112723350525
Inter Cos: 0.11857061833143234
Norm Quadratic Average: 68.5404281616211
Nearest Class Center Accuracy: 0.8305

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.13901548087596893
Inter Cos: 0.1365918666124344
Norm Quadratic Average: 41.752281188964844
Nearest Class Center Accuracy: 0.85075

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1393212080001831
Inter Cos: 0.12893688678741455
Norm Quadratic Average: 43.86213302612305
Nearest Class Center Accuracy: 0.868875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16720835864543915
Inter Cos: 0.10976245999336243
Norm Quadratic Average: 27.2488956451416
Nearest Class Center Accuracy: 0.916

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1793992817401886
Inter Cos: 0.09822042286396027
Norm Quadratic Average: 28.402019500732422
Nearest Class Center Accuracy: 0.944125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20484302937984467
Inter Cos: 0.08463723212480545
Norm Quadratic Average: 19.290464401245117
Nearest Class Center Accuracy: 0.982875

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3144047260284424
Inter Cos: 0.09059356153011322
Norm Quadratic Average: 15.239081382751465
Nearest Class Center Accuracy: 0.998625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.75745391845703
Linear Weight Rank: 4031
Intra Cos: 0.5508442521095276
Inter Cos: 0.10674555599689484
Norm Quadratic Average: 100.42254638671875
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.244239807128906
Linear Weight Rank: 3670
Intra Cos: 0.705443799495697
Inter Cos: 0.12770767509937286
Norm Quadratic Average: 49.531803131103516
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9268537759780884
Linear Weight Rank: 10
Intra Cos: 0.8147850632667542
Inter Cos: 0.14380215108394623
Norm Quadratic Average: 29.40902328491211
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9151291847229004
Inter Cos: 0.21442811191082
Norm Quadratic Average: 15.146442413330078
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.08293811899423599
Accuracy: 0.975
NC1 Within Class Collapse: 1.6196084022521973
NC2 Equinorm: Features: 0.05833716690540314, Weights: 0.014204957522451878
NC2 Equiangle: Features: 0.197476323445638, Weights: 0.08802310625712077
NC3 Self-Duality: 0.5184124112129211
NC4 NCC Mismatch: 0.0030000000000000027

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
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: 0.12241167575120926
Inter Cos: 0.1260620653629303
Norm Quadratic Average: 67.412109375
Nearest Class Center Accuracy: 0.821

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15621143579483032
Inter Cos: 0.14217714965343475
Norm Quadratic Average: 41.345054626464844
Nearest Class Center Accuracy: 0.84

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14869588613510132
Inter Cos: 0.12910693883895874
Norm Quadratic Average: 43.51655960083008
Nearest Class Center Accuracy: 0.8585

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15856482088565826
Inter Cos: 0.11106995493173599
Norm Quadratic Average: 27.205230712890625
Nearest Class Center Accuracy: 0.9055

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1666005253791809
Inter Cos: 0.1092972606420517
Norm Quadratic Average: 28.45865821838379
Nearest Class Center Accuracy: 0.925

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2070583552122116
Inter Cos: 0.09176193922758102
Norm Quadratic Average: 19.292177200317383
Nearest Class Center Accuracy: 0.956

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2641349136829376
Inter Cos: 0.10114006698131561
Norm Quadratic Average: 15.155470848083496
Nearest Class Center Accuracy: 0.971

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.75745391845703
Linear Weight Rank: 4031
Intra Cos: 0.4487677812576294
Inter Cos: 0.1144055724143982
Norm Quadratic Average: 98.16659545898438
Nearest Class Center Accuracy: 0.975

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.244239807128906
Linear Weight Rank: 3670
Intra Cos: 0.5842821598052979
Inter Cos: 0.1405484825372696
Norm Quadratic Average: 48.136878967285156
Nearest Class Center Accuracy: 0.9755

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.9268537759780884
Linear Weight Rank: 10
Intra Cos: 0.6917840838432312
Inter Cos: 0.16268233954906464
Norm Quadratic Average: 28.49090576171875
Nearest Class Center Accuracy: 0.974

Output Layer:
Intra Cos: 0.7987655997276306
Inter Cos: 0.2193686068058014
Norm Quadratic Average: 14.648120880126953
Nearest Class Center Accuracy: 0.972

