Model save path: ./New_Models/bn_False_dataset_CIFAR10_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_test_samples_None_train_samples_None_weight_decay_0.005.pth.tar
Training Set:
Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0198909230530262
Inter Cos: 0.10477276891469955
Norm Quadratic Average: 27.59718894958496
Nearest Class Center Accuracy: 0.26968

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02365526556968689
Inter Cos: 0.10157455503940582
Norm Quadratic Average: 27.660951614379883
Nearest Class Center Accuracy: 0.34158

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.031524594873189926
Inter Cos: 0.11449864506721497
Norm Quadratic Average: 25.964296340942383
Nearest Class Center Accuracy: 0.40616

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03334672003984451
Inter Cos: 0.09815121442079544
Norm Quadratic Average: 24.591567993164062
Nearest Class Center Accuracy: 0.48218

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03546532616019249
Inter Cos: 0.08213435113430023
Norm Quadratic Average: 7.976631164550781
Nearest Class Center Accuracy: 0.58374

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.08655412495136261
Inter Cos: 0.1416665017604828
Norm Quadratic Average: 2.4025003910064697
Nearest Class Center Accuracy: 0.66644

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3296058773994446
Inter Cos: 0.38627752661705017
Norm Quadratic Average: 0.8255199193954468
Nearest Class Center Accuracy: 0.7832

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.5555233955383301
Inter Cos: 0.4127243757247925
Norm Quadratic Average: 0.9819448590278625
Nearest Class Center Accuracy: 0.9443

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.41276216506958
Linear Weight Rank: 53
Intra Cos: 0.6872197389602661
Inter Cos: 0.4006199240684509
Norm Quadratic Average: 7.802921295166016
Nearest Class Center Accuracy: 0.9852

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 3.4185519218444824
Linear Weight Rank: 2856
Intra Cos: 0.7636739015579224
Inter Cos: 0.3894997835159302
Norm Quadratic Average: 9.80057430267334
Nearest Class Center Accuracy: 0.99562

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.4127719402313232
Linear Weight Rank: 9
Intra Cos: 0.7995430827140808
Inter Cos: 0.34946176409721375
Norm Quadratic Average: 11.973305702209473
Nearest Class Center Accuracy: 0.99832

Output Layer:
Intra Cos: 0.7895115613937378
Inter Cos: 0.36043503880500793
Norm Quadratic Average: 16.915790557861328
Nearest Class Center Accuracy: 0.9996

Test Set:
Average Loss: 0.9968051389217377
Accuracy: 0.7671
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.2710196375846863, Weights: 0.07189767807722092
NC2 Equiangle: Features: 0.35894156561957463, Weights: 0.21122478908962675
NC3 Self-Duality: 0.23447610437870026
NC4 NCC Mismatch: 0.0696

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018526077270507812
Inter Cos: 0.1042705774307251
Norm Quadratic Average: 27.550140380859375
Nearest Class Center Accuracy: 0.284

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.023776426911354065
Inter Cos: 0.10234770178794861
Norm Quadratic Average: 27.618106842041016
Nearest Class Center Accuracy: 0.3587

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.030887886881828308
Inter Cos: 0.11608533561229706
Norm Quadratic Average: 25.968061447143555
Nearest Class Center Accuracy: 0.4164

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03187016397714615
Inter Cos: 0.09906119853258133
Norm Quadratic Average: 24.61924171447754
Nearest Class Center Accuracy: 0.4868

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.032099027186632156
Inter Cos: 0.08340892940759659
Norm Quadratic Average: 7.990610122680664
Nearest Class Center Accuracy: 0.5801

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.07676678150892258
Inter Cos: 0.14128288626670837
Norm Quadratic Average: 2.4057059288024902
Nearest Class Center Accuracy: 0.6394

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26677894592285156
Inter Cos: 0.3751113712787628
Norm Quadratic Average: 0.824731707572937
Nearest Class Center Accuracy: 0.6636

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3993501663208008
Inter Cos: 0.40722063183784485
Norm Quadratic Average: 0.973963737487793
Nearest Class Center Accuracy: 0.732

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 3.41276216506958
Linear Weight Rank: 53
Intra Cos: 0.4512731432914734
Inter Cos: 0.4117128252983093
Norm Quadratic Average: 7.702658176422119
Nearest Class Center Accuracy: 0.7548

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 3.4185519218444824
Linear Weight Rank: 2856
Intra Cos: 0.45470312237739563
Inter Cos: 0.3913910388946533
Norm Quadratic Average: 9.632857322692871
Nearest Class Center Accuracy: 0.756

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 3.4127719402313232
Linear Weight Rank: 9
Intra Cos: 0.43523988127708435
Inter Cos: 0.3632044792175293
Norm Quadratic Average: 11.723806381225586
Nearest Class Center Accuracy: 0.7576

Output Layer:
Intra Cos: 0.43419817090034485
Inter Cos: 0.3714841604232788
Norm Quadratic Average: 16.508743286132812
Nearest Class Center Accuracy: 0.7551

