Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_weight_decay_0.03.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: 23.532936096191406
Nearest Class Center Accuracy: 0.81175

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10538170486688614
Inter Cos: 0.12070126831531525
Norm Quadratic Average: 20.46676254272461
Nearest Class Center Accuracy: 0.836125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1541777402162552
Inter Cos: 0.14057424664497375
Norm Quadratic Average: 14.375669479370117
Nearest Class Center Accuracy: 0.8555

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1628732532262802
Inter Cos: 0.13165201246738434
Norm Quadratic Average: 13.31772232055664
Nearest Class Center Accuracy: 0.88525

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2011212408542633
Inter Cos: 0.11610132455825806
Norm Quadratic Average: 8.039915084838867
Nearest Class Center Accuracy: 0.937125

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2416885644197464
Inter Cos: 0.1301136016845703
Norm Quadratic Average: 8.128960609436035
Nearest Class Center Accuracy: 0.972125

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.36140260100364685
Inter Cos: 0.13002604246139526
Norm Quadratic Average: 5.569655895233154
Nearest Class Center Accuracy: 0.99825

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6946207880973816
Inter Cos: 0.1705305427312851
Norm Quadratic Average: 4.656217098236084
Nearest Class Center Accuracy: 1.0

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 23.994991302490234
Linear Weight Rank: 4031
Intra Cos: 0.9459488987922668
Inter Cos: 0.17533569037914276
Norm Quadratic Average: 52.19160079956055
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.789505958557129
Linear Weight Rank: 3670
Intra Cos: 0.9813565611839294
Inter Cos: 0.19008296728134155
Norm Quadratic Average: 25.67719268798828
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5563958883285522
Linear Weight Rank: 10
Intra Cos: 0.9842395186424255
Inter Cos: 0.22517529129981995
Norm Quadratic Average: 14.815633773803711
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9874580502510071
Inter Cos: 0.3125077784061432
Norm Quadratic Average: 9.104180335998535
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.06862346410751342
Accuracy: 0.985
NC1 Within Class Collapse: 0.758090078830719
NC2 Equinorm: Features: 0.08154274523258209, Weights: 0.026094546541571617
NC2 Equiangle: Features: 0.22141270107693142, Weights: 0.13989815182156032
NC3 Self-Duality: 0.09718906134366989
NC4 NCC Mismatch: 0.0014999999999999458

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: 0.12119922786951065
Inter Cos: 0.1307123303413391
Norm Quadratic Average: 20.1390438079834
Nearest Class Center Accuracy: 0.8275

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14882974326610565
Inter Cos: 0.16080856323242188
Norm Quadratic Average: 14.15134334564209
Nearest Class Center Accuracy: 0.8505

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15476666390895844
Inter Cos: 0.15236401557922363
Norm Quadratic Average: 13.137720108032227
Nearest Class Center Accuracy: 0.8755

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19010081887245178
Inter Cos: 0.1405535340309143
Norm Quadratic Average: 7.974510192871094
Nearest Class Center Accuracy: 0.9235

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2230415642261505
Inter Cos: 0.1497107893228531
Norm Quadratic Average: 8.086758613586426
Nearest Class Center Accuracy: 0.953

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.33953893184661865
Inter Cos: 0.14020955562591553
Norm Quadratic Average: 5.51466703414917
Nearest Class Center Accuracy: 0.9735

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.6192510724067688
Inter Cos: 0.18524685502052307
Norm Quadratic Average: 4.541360855102539
Nearest Class Center Accuracy: 0.982

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 23.994991302490234
Linear Weight Rank: 4031
Intra Cos: 0.8546077013015747
Inter Cos: 0.19336499273777008
Norm Quadratic Average: 50.048587799072266
Nearest Class Center Accuracy: 0.984

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 9.789505958557129
Linear Weight Rank: 3670
Intra Cos: 0.8966162800788879
Inter Cos: 0.2040189653635025
Norm Quadratic Average: 24.601144790649414
Nearest Class Center Accuracy: 0.986

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 1.5563958883285522
Linear Weight Rank: 10
Intra Cos: 0.8982530832290649
Inter Cos: 0.202332004904747
Norm Quadratic Average: 14.226016998291016
Nearest Class Center Accuracy: 0.9855

Output Layer:
Intra Cos: 0.9055485129356384
Inter Cos: 0.28138259053230286
Norm Quadratic Average: 8.722919464111328
Nearest Class Center Accuracy: 0.9845

