Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_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: 0.08946067094802856
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: 0.11345934122800827
Inter Cos: 0.1322965919971466
Norm Quadratic Average: 41.93640899658203
Nearest Class Center Accuracy: 0.820125

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15784206986427307
Inter Cos: 0.1679849773645401
Norm Quadratic Average: 40.76289367675781
Nearest Class Center Accuracy: 0.807125

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17848019301891327
Inter Cos: 0.18606236577033997
Norm Quadratic Average: 50.458953857421875
Nearest Class Center Accuracy: 0.8155

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1999402642250061
Inter Cos: 0.1887074112892151
Norm Quadratic Average: 31.758407592773438
Nearest Class Center Accuracy: 0.849625

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.23087191581726074
Inter Cos: 0.21022334694862366
Norm Quadratic Average: 26.963781356811523
Nearest Class Center Accuracy: 0.89975

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3084585666656494
Inter Cos: 0.19138570129871368
Norm Quadratic Average: 14.903890609741211
Nearest Class Center Accuracy: 0.945

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.44873303174972534
Inter Cos: 0.24586385488510132
Norm Quadratic Average: 10.738511085510254
Nearest Class Center Accuracy: 0.98

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.76782989501953
Linear Weight Rank: 4031
Intra Cos: 0.6645143628120422
Inter Cos: 0.2815941572189331
Norm Quadratic Average: 47.89128875732422
Nearest Class Center Accuracy: 0.997125

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.264869689941406
Linear Weight Rank: 3671
Intra Cos: 0.7471163868904114
Inter Cos: 0.282079815864563
Norm Quadratic Average: 32.072628021240234
Nearest Class Center Accuracy: 0.999

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2708916664123535
Linear Weight Rank: 10
Intra Cos: 0.7718870639801025
Inter Cos: 0.26980820298194885
Norm Quadratic Average: 25.390644073486328
Nearest Class Center Accuracy: 0.999375

Output Layer:
Intra Cos: 0.7877947688102722
Inter Cos: 0.30333536863327026
Norm Quadratic Average: 19.021705627441406
Nearest Class Center Accuracy: 0.999125

Test Set:
Average Loss: 0.06832759523391724
Accuracy: 0.979
NC1 Within Class Collapse: 1.9678599834442139
NC2 Equinorm: Features: 0.12691618502140045, Weights: 0.020171821117401123
NC2 Equiangle: Features: 0.26226285298665364, Weights: 0.11143758561876085
NC3 Self-Duality: 0.4176389276981354
NC4 NCC Mismatch: 0.010000000000000009

Layer 0: Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.10133805871009827
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: 0.13485534489154816
Inter Cos: 0.15037010610103607
Norm Quadratic Average: 41.06272506713867
Nearest Class Center Accuracy: 0.8115

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17295241355895996
Inter Cos: 0.2064334750175476
Norm Quadratic Average: 39.97660446166992
Nearest Class Center Accuracy: 0.808

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18428859114646912
Inter Cos: 0.2258903831243515
Norm Quadratic Average: 49.45930099487305
Nearest Class Center Accuracy: 0.8155

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.18257716298103333
Inter Cos: 0.22238503396511078
Norm Quadratic Average: 31.109027862548828
Nearest Class Center Accuracy: 0.8415

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.21312788128852844
Inter Cos: 0.24314425885677338
Norm Quadratic Average: 26.48226547241211
Nearest Class Center Accuracy: 0.8895

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2841276526451111
Inter Cos: 0.20992322266101837
Norm Quadratic Average: 14.60893440246582
Nearest Class Center Accuracy: 0.931

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.40560901165008545
Inter Cos: 0.240624338388443
Norm Quadratic Average: 10.49145221710205
Nearest Class Center Accuracy: 0.959

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 79.76782989501953
Linear Weight Rank: 4031
Intra Cos: 0.6014917492866516
Inter Cos: 0.2796098291873932
Norm Quadratic Average: 46.50393295288086
Nearest Class Center Accuracy: 0.9705

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 32.264869689941406
Linear Weight Rank: 3671
Intra Cos: 0.6760191917419434
Inter Cos: 0.2641696035861969
Norm Quadratic Average: 31.082731246948242
Nearest Class Center Accuracy: 0.9765

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.2708916664123535
Linear Weight Rank: 10
Intra Cos: 0.695757269859314
Inter Cos: 0.2626088261604309
Norm Quadratic Average: 24.626903533935547
Nearest Class Center Accuracy: 0.9765

Output Layer:
Intra Cos: 0.7011752724647522
Inter Cos: 0.3311171531677246
Norm Quadratic Average: 18.43304443359375
Nearest Class Center Accuracy: 0.9765

