Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_314159_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: 0.08946067839860916
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: 0.10168676823377609
Inter Cos: 0.12440453469753265
Norm Quadratic Average: 84.48624420166016
Nearest Class Center Accuracy: 0.8305

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14158639311790466
Inter Cos: 0.12997712194919586
Norm Quadratic Average: 56.053504943847656
Nearest Class Center Accuracy: 0.84725

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14247043430805206
Inter Cos: 0.11441022902727127
Norm Quadratic Average: 57.008358001708984
Nearest Class Center Accuracy: 0.87025

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16795241832733154
Inter Cos: 0.09748295694589615
Norm Quadratic Average: 34.947933197021484
Nearest Class Center Accuracy: 0.905125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17595432698726654
Inter Cos: 0.09117059409618378
Norm Quadratic Average: 35.52314376831055
Nearest Class Center Accuracy: 0.930625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18997472524642944
Inter Cos: 0.09545381367206573
Norm Quadratic Average: 24.06272315979004
Nearest Class Center Accuracy: 0.96925

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27291613817214966
Inter Cos: 0.10332515090703964
Norm Quadratic Average: 18.630674362182617
Nearest Class Center Accuracy: 0.99575

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.9278793334961
Linear Weight Rank: 4031
Intra Cos: 0.46393805742263794
Inter Cos: 0.13911083340644836
Norm Quadratic Average: 117.49427032470703
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.40351486206055
Linear Weight Rank: 3671
Intra Cos: 0.6023231744766235
Inter Cos: 0.16747534275054932
Norm Quadratic Average: 63.92900848388672
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.272174835205078
Linear Weight Rank: 10
Intra Cos: 0.7376194596290588
Inter Cos: 0.19535571336746216
Norm Quadratic Average: 40.866676330566406
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9012531042098999
Inter Cos: 0.293211430311203
Norm Quadratic Average: 22.03490447998047
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.09217573982477188
Accuracy: 0.9745
NC1 Within Class Collapse: 1.694688320159912
NC2 Equinorm: Features: 0.06670144200325012, Weights: 0.010264579206705093
NC2 Equiangle: Features: 0.2029807620578342, Weights: 0.08505173789130317
NC3 Self-Duality: 0.6413178443908691
NC4 NCC Mismatch: 0.011499999999999955

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: 0.1266184151172638
Inter Cos: 0.1344129741191864
Norm Quadratic Average: 83.55086517333984
Nearest Class Center Accuracy: 0.823

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1552239954471588
Inter Cos: 0.15919721126556396
Norm Quadratic Average: 55.85211181640625
Nearest Class Center Accuracy: 0.8375

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14270034432411194
Inter Cos: 0.14232458174228668
Norm Quadratic Average: 56.82623291015625
Nearest Class Center Accuracy: 0.856

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15684285759925842
Inter Cos: 0.12159211933612823
Norm Quadratic Average: 34.981075286865234
Nearest Class Center Accuracy: 0.903

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16895602643489838
Inter Cos: 0.11375826597213745
Norm Quadratic Average: 35.66633224487305
Nearest Class Center Accuracy: 0.9215

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19606316089630127
Inter Cos: 0.10215839743614197
Norm Quadratic Average: 24.175811767578125
Nearest Class Center Accuracy: 0.9465

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26590779423713684
Inter Cos: 0.10540889948606491
Norm Quadratic Average: 18.59364128112793
Nearest Class Center Accuracy: 0.9685

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 99.9278793334961
Linear Weight Rank: 4031
Intra Cos: 0.4068152606487274
Inter Cos: 0.1406293511390686
Norm Quadratic Average: 115.35752868652344
Nearest Class Center Accuracy: 0.974

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.40351486206055
Linear Weight Rank: 3671
Intra Cos: 0.5222623348236084
Inter Cos: 0.1693081110715866
Norm Quadratic Average: 62.353851318359375
Nearest Class Center Accuracy: 0.974

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.272174835205078
Linear Weight Rank: 10
Intra Cos: 0.6342270374298096
Inter Cos: 0.20003749430179596
Norm Quadratic Average: 39.70139694213867
Nearest Class Center Accuracy: 0.9705

Output Layer:
Intra Cos: 0.7909107208251953
Inter Cos: 0.2743314504623413
Norm Quadratic Average: 21.27940559387207
Nearest Class Center Accuracy: 0.969

