Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_338327_weight_decay_0.0005.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: 0.11311887949705124
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: 0.11439689248800278
Inter Cos: 0.13462182879447937
Norm Quadratic Average: 48.49870681762695
Nearest Class Center Accuracy: 0.821625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.153237447142601
Inter Cos: 0.16989195346832275
Norm Quadratic Average: 47.296016693115234
Nearest Class Center Accuracy: 0.802125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16655927896499634
Inter Cos: 0.18149405717849731
Norm Quadratic Average: 62.149478912353516
Nearest Class Center Accuracy: 0.808875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18293850123882294
Inter Cos: 0.17904819548130035
Norm Quadratic Average: 40.43738555908203
Nearest Class Center Accuracy: 0.852875

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20306383073329926
Inter Cos: 0.208387553691864
Norm Quadratic Average: 39.836036682128906
Nearest Class Center Accuracy: 0.8925

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2668229937553406
Inter Cos: 0.19389887154102325
Norm Quadratic Average: 23.48360252380371
Nearest Class Center Accuracy: 0.937125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.38452279567718506
Inter Cos: 0.21695737540721893
Norm Quadratic Average: 18.53112030029297
Nearest Class Center Accuracy: 0.974875

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.98066711425781
Linear Weight Rank: 4031
Intra Cos: 0.6041089296340942
Inter Cos: 0.23433052003383636
Norm Quadratic Average: 80.86932373046875
Nearest Class Center Accuracy: 0.9975

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.004676818847656
Linear Weight Rank: 3670
Intra Cos: 0.7190802097320557
Inter Cos: 0.23552829027175903
Norm Quadratic Average: 51.9803466796875
Nearest Class Center Accuracy: 0.999625

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.473674774169922
Linear Weight Rank: 10
Intra Cos: 0.7737107872962952
Inter Cos: 0.258190393447876
Norm Quadratic Average: 40.17774200439453
Nearest Class Center Accuracy: 0.999875

Output Layer:
Intra Cos: 0.8264883756637573
Inter Cos: 0.3664318025112152
Norm Quadratic Average: 28.7755126953125
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.08247112679481507
Accuracy: 0.979
NC1 Within Class Collapse: 1.830433964729309
NC2 Equinorm: Features: 0.10338973999023438, Weights: 0.013189132325351238
NC2 Equiangle: Features: 0.2431360880533854, Weights: 0.09762076271904839
NC3 Self-Duality: 0.5481017231941223
NC4 NCC Mismatch: 0.01100000000000001

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133808106184006
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: 0.13510775566101074
Inter Cos: 0.15130358934402466
Norm Quadratic Average: 47.162017822265625
Nearest Class Center Accuracy: 0.814

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17062349617481232
Inter Cos: 0.20054347813129425
Norm Quadratic Average: 45.98036575317383
Nearest Class Center Accuracy: 0.8015

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18021343648433685
Inter Cos: 0.2217240184545517
Norm Quadratic Average: 60.280452728271484
Nearest Class Center Accuracy: 0.8135

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16452656686306
Inter Cos: 0.2159946709871292
Norm Quadratic Average: 39.403228759765625
Nearest Class Center Accuracy: 0.845

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18116360902786255
Inter Cos: 0.2416522055864334
Norm Quadratic Average: 38.87628173828125
Nearest Class Center Accuracy: 0.886

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23909282684326172
Inter Cos: 0.22009728848934174
Norm Quadratic Average: 22.9219913482666
Nearest Class Center Accuracy: 0.9285

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.34141021966934204
Inter Cos: 0.2485959827899933
Norm Quadratic Average: 17.971317291259766
Nearest Class Center Accuracy: 0.9525

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 98.98066711425781
Linear Weight Rank: 4031
Intra Cos: 0.5289027094841003
Inter Cos: 0.261658638715744
Norm Quadratic Average: 77.67256927490234
Nearest Class Center Accuracy: 0.97

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.004676818847656
Linear Weight Rank: 3670
Intra Cos: 0.6330354809761047
Inter Cos: 0.25358131527900696
Norm Quadratic Average: 49.823631286621094
Nearest Class Center Accuracy: 0.975

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.473674774169922
Linear Weight Rank: 10
Intra Cos: 0.6819872856140137
Inter Cos: 0.2433791607618332
Norm Quadratic Average: 38.52814483642578
Nearest Class Center Accuracy: 0.9755

Output Layer:
Intra Cos: 0.7223077416419983
Inter Cos: 0.34789609909057617
Norm Quadratic Average: 27.55923843383789
Nearest Class Center Accuracy: 0.9745

