Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_846264_weight_decay_0.003.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08946066349744797
Inter Cos: 0.11311887949705124
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: 0.10162120312452316
Inter Cos: 0.125931054353714
Norm Quadratic Average: 78.6841812133789
Nearest Class Center Accuracy: 0.83175

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14296863973140717
Inter Cos: 0.13454613089561462
Norm Quadratic Average: 49.36806869506836
Nearest Class Center Accuracy: 0.848625

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14150911569595337
Inter Cos: 0.1245698481798172
Norm Quadratic Average: 49.76662826538086
Nearest Class Center Accuracy: 0.869125

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16951191425323486
Inter Cos: 0.10005363076925278
Norm Quadratic Average: 30.398834228515625
Nearest Class Center Accuracy: 0.90675

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.176779642701149
Inter Cos: 0.09514971077442169
Norm Quadratic Average: 31.43159294128418
Nearest Class Center Accuracy: 0.934625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21319632232189178
Inter Cos: 0.08933013677597046
Norm Quadratic Average: 21.459674835205078
Nearest Class Center Accuracy: 0.975125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.30698710680007935
Inter Cos: 0.09795504063367844
Norm Quadratic Average: 16.67026710510254
Nearest Class Center Accuracy: 0.997

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.77911376953125
Linear Weight Rank: 4031
Intra Cos: 0.5276729464530945
Inter Cos: 0.13764652609825134
Norm Quadratic Average: 107.35726928710938
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.492923736572266
Linear Weight Rank: 3671
Intra Cos: 0.6803023219108582
Inter Cos: 0.15364129841327667
Norm Quadratic Average: 54.4561653137207
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0562992095947266
Linear Weight Rank: 10
Intra Cos: 0.7921782732009888
Inter Cos: 0.155472069978714
Norm Quadratic Average: 33.007266998291016
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9130748510360718
Inter Cos: 0.25394076108932495
Norm Quadratic Average: 17.168367385864258
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.08610782182216645
Accuracy: 0.977
NC1 Within Class Collapse: 1.5888259410858154
NC2 Equinorm: Features: 0.06305867433547974, Weights: 0.01294771023094654
NC2 Equiangle: Features: 0.20063495635986328, Weights: 0.08440349896748861
NC3 Self-Duality: 0.571951150894165
NC4 NCC Mismatch: 0.0050000000000000044

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133806616067886
Inter Cos: 0.11957792937755585
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: 0.12977376580238342
Inter Cos: 0.13378815352916718
Norm Quadratic Average: 77.23320007324219
Nearest Class Center Accuracy: 0.825

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15356460213661194
Inter Cos: 0.1562163382768631
Norm Quadratic Average: 48.89862060546875
Nearest Class Center Accuracy: 0.8455

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14740975201129913
Inter Cos: 0.1391884982585907
Norm Quadratic Average: 49.36213684082031
Nearest Class Center Accuracy: 0.861

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15941019356250763
Inter Cos: 0.12213418632745743
Norm Quadratic Average: 30.273462295532227
Nearest Class Center Accuracy: 0.903

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16392959654331207
Inter Cos: 0.11356277018785477
Norm Quadratic Average: 31.35918426513672
Nearest Class Center Accuracy: 0.9275

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1952187716960907
Inter Cos: 0.08865214139223099
Norm Quadratic Average: 21.379661560058594
Nearest Class Center Accuracy: 0.9555

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2692778706550598
Inter Cos: 0.09975218027830124
Norm Quadratic Average: 16.550661087036133
Nearest Class Center Accuracy: 0.969

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 87.77911376953125
Linear Weight Rank: 4031
Intra Cos: 0.440196692943573
Inter Cos: 0.12828543782234192
Norm Quadratic Average: 105.33072662353516
Nearest Class Center Accuracy: 0.9745

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.492923736572266
Linear Weight Rank: 3671
Intra Cos: 0.5754303932189941
Inter Cos: 0.13604232668876648
Norm Quadratic Average: 53.11440658569336
Nearest Class Center Accuracy: 0.9775

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.0562992095947266
Linear Weight Rank: 10
Intra Cos: 0.6841928958892822
Inter Cos: 0.14979848265647888
Norm Quadratic Average: 32.101993560791016
Nearest Class Center Accuracy: 0.9765

Output Layer:
Intra Cos: 0.8105042576789856
Inter Cos: 0.24362145364284515
Norm Quadratic Average: 16.650943756103516
Nearest Class Center Accuracy: 0.9775

