Model save path: ./New_Models/bn_True_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_weight_decay_0.001.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: 0.10494820773601532
Inter Cos: 0.12047575414180756
Norm Quadratic Average: 82.77362060546875
Nearest Class Center Accuracy: 0.83575

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14444255828857422
Inter Cos: 0.135491281747818
Norm Quadratic Average: 57.961761474609375
Nearest Class Center Accuracy: 0.848125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14443448185920715
Inter Cos: 0.1217551976442337
Norm Quadratic Average: 54.40330505371094
Nearest Class Center Accuracy: 0.870625

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16169214248657227
Inter Cos: 0.09972996264696121
Norm Quadratic Average: 33.06569290161133
Nearest Class Center Accuracy: 0.905375

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16745170950889587
Inter Cos: 0.0861387699842453
Norm Quadratic Average: 34.1124382019043
Nearest Class Center Accuracy: 0.9315

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19373303651809692
Inter Cos: 0.07255349308252335
Norm Quadratic Average: 23.08177947998047
Nearest Class Center Accuracy: 0.971125

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2742976248264313
Inter Cos: 0.08720449358224869
Norm Quadratic Average: 18.10123062133789
Nearest Class Center Accuracy: 0.99575

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.62397003173828
Linear Weight Rank: 4031
Intra Cos: 0.49219444394111633
Inter Cos: 0.12521396577358246
Norm Quadratic Average: 114.74275207519531
Nearest Class Center Accuracy: 1.0

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.053993225097656
Linear Weight Rank: 3671
Intra Cos: 0.634855329990387
Inter Cos: 0.1586741954088211
Norm Quadratic Average: 61.48865509033203
Nearest Class Center Accuracy: 1.0

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2116646766662598
Linear Weight Rank: 10
Intra Cos: 0.7505895495414734
Inter Cos: 0.18366870284080505
Norm Quadratic Average: 38.96242141723633
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.8978244066238403
Inter Cos: 0.2680583596229553
Norm Quadratic Average: 21.20648193359375
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.09445352107286453
Accuracy: 0.9715
NC1 Within Class Collapse: 1.6651983261108398
NC2 Equinorm: Features: 0.08231326937675476, Weights: 0.01707358844578266
NC2 Equiangle: Features: 0.2142630894978841, Weights: 0.08870429462856716
NC3 Self-Duality: 0.6381222009658813
NC4 NCC Mismatch: 0.01100000000000001

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: 0.12078554183244705
Inter Cos: 0.13027964532375336
Norm Quadratic Average: 81.43820190429688
Nearest Class Center Accuracy: 0.825

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.14288900792598724
Inter Cos: 0.15187880396842957
Norm Quadratic Average: 57.03400421142578
Nearest Class Center Accuracy: 0.841

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1410875916481018
Inter Cos: 0.13999812304973602
Norm Quadratic Average: 53.59782791137695
Nearest Class Center Accuracy: 0.863

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1522592157125473
Inter Cos: 0.1148202046751976
Norm Quadratic Average: 32.81044006347656
Nearest Class Center Accuracy: 0.9

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15663594007492065
Inter Cos: 0.10380860418081284
Norm Quadratic Average: 33.8774299621582
Nearest Class Center Accuracy: 0.92

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18765410780906677
Inter Cos: 0.0890204906463623
Norm Quadratic Average: 22.87157440185547
Nearest Class Center Accuracy: 0.9465

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.25112757086753845
Inter Cos: 0.0967106744647026
Norm Quadratic Average: 17.88393211364746
Nearest Class Center Accuracy: 0.969

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 96.62397003173828
Linear Weight Rank: 4031
Intra Cos: 0.4057919681072235
Inter Cos: 0.12208867073059082
Norm Quadratic Average: 112.21928405761719
Nearest Class Center Accuracy: 0.973

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 39.053993225097656
Linear Weight Rank: 3671
Intra Cos: 0.5260770916938782
Inter Cos: 0.15603341162204742
Norm Quadratic Average: 59.83586883544922
Nearest Class Center Accuracy: 0.9735

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2116646766662598
Linear Weight Rank: 10
Intra Cos: 0.6302742958068848
Inter Cos: 0.1849321722984314
Norm Quadratic Average: 37.77627182006836
Nearest Class Center Accuracy: 0.974

Output Layer:
Intra Cos: 0.770490288734436
Inter Cos: 0.2617303133010864
Norm Quadratic Average: 20.43071174621582
Nearest Class Center Accuracy: 0.973

