Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_weight_decay_0.0001.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: 0.09977442026138306
Inter Cos: 0.12245746701955795
Norm Quadratic Average: 94.9827651977539
Nearest Class Center Accuracy: 0.836625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14596028625965118
Inter Cos: 0.13714241981506348
Norm Quadratic Average: 57.41767120361328
Nearest Class Center Accuracy: 0.858

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14413492381572723
Inter Cos: 0.12549665570259094
Norm Quadratic Average: 56.64276885986328
Nearest Class Center Accuracy: 0.87625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17751038074493408
Inter Cos: 0.11070840805768967
Norm Quadratic Average: 35.142765045166016
Nearest Class Center Accuracy: 0.91225

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17820242047309875
Inter Cos: 0.09092598408460617
Norm Quadratic Average: 36.31344985961914
Nearest Class Center Accuracy: 0.931625

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19500936567783356
Inter Cos: 0.09583461284637451
Norm Quadratic Average: 24.80186653137207
Nearest Class Center Accuracy: 0.973125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.27443110942840576
Inter Cos: 0.09602097421884537
Norm Quadratic Average: 18.90414810180664
Nearest Class Center Accuracy: 0.995625

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.89171600341797
Linear Weight Rank: 4031
Intra Cos: 0.48184093832969666
Inter Cos: 0.10348765552043915
Norm Quadratic Average: 119.52967834472656
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.776214599609375
Linear Weight Rank: 3671
Intra Cos: 0.6244960427284241
Inter Cos: 0.13483206927776337
Norm Quadratic Average: 64.932861328125
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2876439094543457
Linear Weight Rank: 10
Intra Cos: 0.7419456243515015
Inter Cos: 0.15659262239933014
Norm Quadratic Average: 41.42512893676758
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9068422913551331
Inter Cos: 0.24025177955627441
Norm Quadratic Average: 22.59714698791504
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.10156645859032869
Accuracy: 0.9745
NC1 Within Class Collapse: 1.713214635848999
NC2 Equinorm: Features: 0.06347648054361343, Weights: 0.008622685447335243
NC2 Equiangle: Features: 0.19669371710883246, Weights: 0.08976001739501953
NC3 Self-Duality: 0.6399146914482117
NC4 NCC Mismatch: 0.008000000000000007

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: 0.1254318207502365
Inter Cos: 0.12777157127857208
Norm Quadratic Average: 93.66807556152344
Nearest Class Center Accuracy: 0.8305

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1570991724729538
Inter Cos: 0.1454988270998001
Norm Quadratic Average: 56.92829895019531
Nearest Class Center Accuracy: 0.848

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15215463936328888
Inter Cos: 0.1248539388179779
Norm Quadratic Average: 56.160560607910156
Nearest Class Center Accuracy: 0.8655

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17593221366405487
Inter Cos: 0.1132010817527771
Norm Quadratic Average: 35.12204360961914
Nearest Class Center Accuracy: 0.901

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17814698815345764
Inter Cos: 0.09544496238231659
Norm Quadratic Average: 36.3310546875
Nearest Class Center Accuracy: 0.9205

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1956596076488495
Inter Cos: 0.11189932376146317
Norm Quadratic Average: 24.83847427368164
Nearest Class Center Accuracy: 0.9425

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2544403076171875
Inter Cos: 0.09321944415569305
Norm Quadratic Average: 18.80404281616211
Nearest Class Center Accuracy: 0.97

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.89171600341797
Linear Weight Rank: 4031
Intra Cos: 0.40306738018989563
Inter Cos: 0.10660108923912048
Norm Quadratic Average: 117.02580261230469
Nearest Class Center Accuracy: 0.9745

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.776214599609375
Linear Weight Rank: 3671
Intra Cos: 0.5275647640228271
Inter Cos: 0.13380302488803864
Norm Quadratic Average: 63.14328384399414
Nearest Class Center Accuracy: 0.974

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2876439094543457
Linear Weight Rank: 10
Intra Cos: 0.6348232626914978
Inter Cos: 0.15740257501602173
Norm Quadratic Average: 40.07783126831055
Nearest Class Center Accuracy: 0.9755

Output Layer:
Intra Cos: 0.7995211482048035
Inter Cos: 0.2750340700149536
Norm Quadratic Average: 21.695018768310547
Nearest Class Center Accuracy: 0.975

