Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_200_lr_0.01_model_type_vgg11_rand_seed_265358_test_samples_None_train_samples_None_weight_decay_0.0003.pth.tar
Training Set:
Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.09116753190755844
Inter Cos: 0.10967151820659637
Norm Quadratic Average: 23.567670822143555
Nearest Class Center Accuracy: 0.8079833333333334

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.11342952400445938
Inter Cos: 0.13028712570667267
Norm Quadratic Average: 35.288368225097656
Nearest Class Center Accuracy: 0.8295666666666667

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1907581090927124
Inter Cos: 0.1691843420267105
Norm Quadratic Average: 32.76496124267578
Nearest Class Center Accuracy: 0.8817333333333334

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2231786698102951
Inter Cos: 0.18963775038719177
Norm Quadratic Average: 32.26680374145508
Nearest Class Center Accuracy: 0.9107666666666666

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2641221880912781
Inter Cos: 0.1836179792881012
Norm Quadratic Average: 15.05908489227295
Nearest Class Center Accuracy: 0.95765

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4211769104003906
Inter Cos: 0.23474615812301636
Norm Quadratic Average: 9.814109802246094
Nearest Class Center Accuracy: 0.9802

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5697466731071472
Inter Cos: 0.27140435576438904
Norm Quadratic Average: 5.391386985778809
Nearest Class Center Accuracy: 0.9945

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8192228674888611
Inter Cos: 0.3093244731426239
Norm Quadratic Average: 4.690920352935791
Nearest Class Center Accuracy: 0.9984

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 31.729598999023438
Linear Weight Rank: 4031
Intra Cos: 0.8975251913070679
Inter Cos: 0.24713297188282013
Norm Quadratic Average: 26.325803756713867
Nearest Class Center Accuracy: 0.9991833333333333

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 13.077335357666016
Linear Weight Rank: 3669
Intra Cos: 0.9259011149406433
Inter Cos: 0.22675025463104248
Norm Quadratic Average: 23.373613357543945
Nearest Class Center Accuracy: 0.99955

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.805203914642334
Linear Weight Rank: 10
Intra Cos: 0.9309791326522827
Inter Cos: 0.24264979362487793
Norm Quadratic Average: 21.19327735900879
Nearest Class Center Accuracy: 0.99965

Output Layer:
Intra Cos: 0.9480014443397522
Inter Cos: 0.31575825810432434
Norm Quadratic Average: 21.174514770507812
Nearest Class Center Accuracy: 0.99995

Test Set:
Average Loss: 0.021735881753638386
Accuracy: 0.9936
NC1 Within Class Collapse: 0.5241817235946655
NC2 Equinorm: Features: 0.10112833976745605, Weights: 0.043387796729803085
NC2 Equiangle: Features: 0.2071910646226671, Weights: 0.1016063478257921
NC3 Self-Duality: 0.1448686420917511
NC4 NCC Mismatch: 0.0030999999999999917

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10219583660364151
Inter Cos: 0.12048852443695068
Norm Quadratic Average: 23.595197677612305
Nearest Class Center Accuracy: 0.8229

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1259053498506546
Inter Cos: 0.14038360118865967
Norm Quadratic Average: 35.214107513427734
Nearest Class Center Accuracy: 0.8427

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2052052617073059
Inter Cos: 0.177132248878479
Norm Quadratic Average: 32.656333923339844
Nearest Class Center Accuracy: 0.8942

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23791447281837463
Inter Cos: 0.19403773546218872
Norm Quadratic Average: 32.16337966918945
Nearest Class Center Accuracy: 0.9215

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2765304148197174
Inter Cos: 0.19482940435409546
Norm Quadratic Average: 15.01274299621582
Nearest Class Center Accuracy: 0.963

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4368954300880432
Inter Cos: 0.2440505176782608
Norm Quadratic Average: 9.805572509765625
Nearest Class Center Accuracy: 0.9807

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.57745760679245
Inter Cos: 0.29262036085128784
Norm Quadratic Average: 5.410435199737549
Nearest Class Center Accuracy: 0.9892

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.8178399801254272
Inter Cos: 0.33192723989486694
Norm Quadratic Average: 4.719712734222412
Nearest Class Center Accuracy: 0.9916

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 31.729598999023438
Linear Weight Rank: 4031
Intra Cos: 0.8969811201095581
Inter Cos: 0.26734983921051025
Norm Quadratic Average: 26.484825134277344
Nearest Class Center Accuracy: 0.9926

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 13.077335357666016
Linear Weight Rank: 3669
Intra Cos: 0.9248496294021606
Inter Cos: 0.24603983759880066
Norm Quadratic Average: 23.509845733642578
Nearest Class Center Accuracy: 0.993

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.805203914642334
Linear Weight Rank: 10
Intra Cos: 0.9293280243873596
Inter Cos: 0.2377733737230301
Norm Quadratic Average: 21.31368064880371
Nearest Class Center Accuracy: 0.9935

Output Layer:
Intra Cos: 0.9416544437408447
Inter Cos: 0.31302565336227417
Norm Quadratic Average: 21.295820236206055
Nearest Class Center Accuracy: 0.9941

