Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_MNIST_epochs_50_lr_0.001_model_type_vgg11_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: 0.08946066349744797
Inter Cos: 0.11311884224414825
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: 0.11586906760931015
Inter Cos: 0.13322897255420685
Norm Quadratic Average: 46.573482513427734
Nearest Class Center Accuracy: 0.8175

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15201514959335327
Inter Cos: 0.1728849858045578
Norm Quadratic Average: 45.36734390258789
Nearest Class Center Accuracy: 0.78975

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16216817498207092
Inter Cos: 0.18938378989696503
Norm Quadratic Average: 58.459903717041016
Nearest Class Center Accuracy: 0.80175

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19270803034305573
Inter Cos: 0.1881272941827774
Norm Quadratic Average: 35.992733001708984
Nearest Class Center Accuracy: 0.839875

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21707291901111603
Inter Cos: 0.2031230479478836
Norm Quadratic Average: 32.081993103027344
Nearest Class Center Accuracy: 0.881375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27912411093711853
Inter Cos: 0.1837613731622696
Norm Quadratic Average: 17.546689987182617
Nearest Class Center Accuracy: 0.933

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.40590161085128784
Inter Cos: 0.2095348834991455
Norm Quadratic Average: 12.961827278137207
Nearest Class Center Accuracy: 0.970875

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 86.84867858886719
Linear Weight Rank: 4031
Intra Cos: 0.6361699104309082
Inter Cos: 0.256273478269577
Norm Quadratic Average: 55.892181396484375
Nearest Class Center Accuracy: 0.995625

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.126564025878906
Linear Weight Rank: 3670
Intra Cos: 0.7451750636100769
Inter Cos: 0.27670618891716003
Norm Quadratic Average: 35.66680908203125
Nearest Class Center Accuracy: 0.999125

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2931230068206787
Linear Weight Rank: 10
Intra Cos: 0.793475329875946
Inter Cos: 0.27875736355781555
Norm Quadratic Average: 27.044652938842773
Nearest Class Center Accuracy: 0.9995

Output Layer:
Intra Cos: 0.8372286558151245
Inter Cos: 0.34950530529022217
Norm Quadratic Average: 18.841354370117188
Nearest Class Center Accuracy: 0.99875

Test Set:
Average Loss: 0.0749485434293747
Accuracy: 0.978
NC1 Within Class Collapse: 2.0460407733917236
NC2 Equinorm: Features: 0.10780473798513412, Weights: 0.01338966004550457
NC2 Equiangle: Features: 0.24797526465521919, Weights: 0.09892856809828017
NC3 Self-Duality: 0.493360698223114
NC4 NCC Mismatch: 0.013499999999999956

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133811086416245
Inter Cos: 0.11957790702581406
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: 0.13621972501277924
Inter Cos: 0.15034523606300354
Norm Quadratic Average: 45.350101470947266
Nearest Class Center Accuracy: 0.811

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16972790658473969
Inter Cos: 0.20341025292873383
Norm Quadratic Average: 44.07745361328125
Nearest Class Center Accuracy: 0.79

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1805947721004486
Inter Cos: 0.22864197194576263
Norm Quadratic Average: 56.671146392822266
Nearest Class Center Accuracy: 0.8015

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17082072794437408
Inter Cos: 0.22852355241775513
Norm Quadratic Average: 35.02106475830078
Nearest Class Center Accuracy: 0.8355

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19011768698692322
Inter Cos: 0.24362269043922424
Norm Quadratic Average: 31.303449630737305
Nearest Class Center Accuracy: 0.87

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.24670951068401337
Inter Cos: 0.20649059116840363
Norm Quadratic Average: 17.11363410949707
Nearest Class Center Accuracy: 0.924

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3590313494205475
Inter Cos: 0.23771819472312927
Norm Quadratic Average: 12.552054405212402
Nearest Class Center Accuracy: 0.9525

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 86.84867858886719
Linear Weight Rank: 4031
Intra Cos: 0.5627860426902771
Inter Cos: 0.2581234276294708
Norm Quadratic Average: 53.71549606323242
Nearest Class Center Accuracy: 0.9695

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 35.126564025878906
Linear Weight Rank: 3670
Intra Cos: 0.6635715365409851
Inter Cos: 0.2671178877353668
Norm Quadratic Average: 34.21127700805664
Nearest Class Center Accuracy: 0.975

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2931230068206787
Linear Weight Rank: 10
Intra Cos: 0.7075838446617126
Inter Cos: 0.2929864823818207
Norm Quadratic Average: 25.947830200195312
Nearest Class Center Accuracy: 0.976

Output Layer:
Intra Cos: 0.7433655858039856
Inter Cos: 0.3880240023136139
Norm Quadratic Average: 18.032838821411133
Nearest Class Center Accuracy: 0.9745

