Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_weight_decay_0.03.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: 0.1214669942855835
Inter Cos: 0.14725977182388306
Norm Quadratic Average: 36.94578552246094
Nearest Class Center Accuracy: 0.803625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15140724182128906
Inter Cos: 0.180059552192688
Norm Quadratic Average: 42.68861389160156
Nearest Class Center Accuracy: 0.771375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16401804983615875
Inter Cos: 0.19871129095554352
Norm Quadratic Average: 57.2957763671875
Nearest Class Center Accuracy: 0.75825

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1750687062740326
Inter Cos: 0.19786295294761658
Norm Quadratic Average: 38.007240295410156
Nearest Class Center Accuracy: 0.774875

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20999935269355774
Inter Cos: 0.24230027198791504
Norm Quadratic Average: 27.994701385498047
Nearest Class Center Accuracy: 0.835125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.28624528646469116
Inter Cos: 0.3351024091243744
Norm Quadratic Average: 16.071701049804688
Nearest Class Center Accuracy: 0.8975

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.39387184381484985
Inter Cos: 0.396491140127182
Norm Quadratic Average: 10.240710258483887
Nearest Class Center Accuracy: 0.944

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 24.013269424438477
Linear Weight Rank: 4031
Intra Cos: 0.5159435272216797
Inter Cos: 0.3781992793083191
Norm Quadratic Average: 42.23505401611328
Nearest Class Center Accuracy: 0.96575

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.829873085021973
Linear Weight Rank: 3670
Intra Cos: 0.5846507549285889
Inter Cos: 0.35056090354919434
Norm Quadratic Average: 27.425790786743164
Nearest Class Center Accuracy: 0.971875

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.781583547592163
Linear Weight Rank: 10
Intra Cos: 0.6101640462875366
Inter Cos: 0.32433685660362244
Norm Quadratic Average: 18.849727630615234
Nearest Class Center Accuracy: 0.973

Output Layer:
Intra Cos: 0.6387785077095032
Inter Cos: 0.44275155663490295
Norm Quadratic Average: 13.962822914123535
Nearest Class Center Accuracy: 0.9715

Test Set:
Average Loss: 0.12989270877838135
Accuracy: 0.962
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.2041933685541153, Weights: 0.047081515192985535
NC2 Equiangle: Features: 0.316399171617296, Weights: 0.19194488525390624
NC3 Self-Duality: 0.1961696296930313
NC4 NCC Mismatch: 0.028000000000000025

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: 0.14326211810112
Inter Cos: 0.17033478617668152
Norm Quadratic Average: 35.7889289855957
Nearest Class Center Accuracy: 0.801

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16407611966133118
Inter Cos: 0.21933510899543762
Norm Quadratic Average: 41.414894104003906
Nearest Class Center Accuracy: 0.7715

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17725718021392822
Inter Cos: 0.24104104936122894
Norm Quadratic Average: 55.4807243347168
Nearest Class Center Accuracy: 0.7625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16339048743247986
Inter Cos: 0.2309073954820633
Norm Quadratic Average: 36.86623764038086
Nearest Class Center Accuracy: 0.7785

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.203572615981102
Inter Cos: 0.26305878162384033
Norm Quadratic Average: 27.21469497680664
Nearest Class Center Accuracy: 0.8375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.278963565826416
Inter Cos: 0.31645411252975464
Norm Quadratic Average: 15.582791328430176
Nearest Class Center Accuracy: 0.8765

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3686462640762329
Inter Cos: 0.3675795793533325
Norm Quadratic Average: 9.887968063354492
Nearest Class Center Accuracy: 0.918

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 24.013269424438477
Linear Weight Rank: 4031
Intra Cos: 0.46412286162376404
Inter Cos: 0.35151785612106323
Norm Quadratic Average: 40.74797821044922
Nearest Class Center Accuracy: 0.9435

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.829873085021973
Linear Weight Rank: 3670
Intra Cos: 0.5154795050621033
Inter Cos: 0.33335644006729126
Norm Quadratic Average: 26.47702407836914
Nearest Class Center Accuracy: 0.95

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.781583547592163
Linear Weight Rank: 10
Intra Cos: 0.5295487642288208
Inter Cos: 0.3386836349964142
Norm Quadratic Average: 18.22077178955078
Nearest Class Center Accuracy: 0.9495

Output Layer:
Intra Cos: 0.5422155261039734
Inter Cos: 0.45246121287345886
Norm Quadratic Average: 13.486607551574707
Nearest Class Center Accuracy: 0.9485

