Model save path: ./New_Models/bn_True_dataset_CIFAR100_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(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022893192246556282
Inter Cos: 0.07011394202709198
Norm Quadratic Average: 29.326324462890625
Nearest Class Center Accuracy: 0.03258

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025107981637120247
Inter Cos: 0.027981657534837723
Norm Quadratic Average: 41.32660675048828
Nearest Class Center Accuracy: 0.04866

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022308388724923134
Inter Cos: 0.024529650807380676
Norm Quadratic Average: 20.924095153808594
Nearest Class Center Accuracy: 0.0602

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01809544675052166
Inter Cos: 0.021029047667980194
Norm Quadratic Average: 19.24514389038086
Nearest Class Center Accuracy: 0.06886

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02441488392651081
Inter Cos: 0.023836452513933182
Norm Quadratic Average: 11.572907447814941
Nearest Class Center Accuracy: 0.0785

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.030336808413267136
Inter Cos: 0.029555728659033775
Norm Quadratic Average: 11.915193557739258
Nearest Class Center Accuracy: 0.08384

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.07129603624343872
Inter Cos: 0.05947132781147957
Norm Quadratic Average: 8.746443748474121
Nearest Class Center Accuracy: 0.09514

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.2686455249786377
Inter Cos: 0.1509312242269516
Norm Quadratic Average: 8.143068313598633
Nearest Class Center Accuracy: 0.09976

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 39.66019058227539
Linear Weight Rank: 4030
Intra Cos: 0.6117613911628723
Inter Cos: 0.2271556556224823
Norm Quadratic Average: 40.57790756225586
Nearest Class Center Accuracy: 0.1

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 19.27256202697754
Linear Weight Rank: 3655
Intra Cos: 0.7964409589767456
Inter Cos: 0.2126307338476181
Norm Quadratic Average: 32.895172119140625
Nearest Class Center Accuracy: 0.1

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 10.086735725402832
Linear Weight Rank: 98
Intra Cos: 0.8473469018936157
Inter Cos: 0.2381811887025833
Norm Quadratic Average: 33.061790466308594
Nearest Class Center Accuracy: 0.1

Output Layer:
Intra Cos: 0.9024831056594849
Inter Cos: 0.4226682484149933
Norm Quadratic Average: 52.179500579833984
Nearest Class Center Accuracy: 0.1

Test Set:
Average Loss: 2.886057814025879
Accuracy: 0.5428
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.27454042434692383, Weights: 0.03483496233820915
NC2 Equiangle: Features: 0.1711999265112058, Weights: 0.0983163791232639
NC3 Self-Duality: 0.47104644775390625
NC4 NCC Mismatch: 0.16159999999999997

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.006621266715228558
Inter Cos: 0.4067547917366028
Norm Quadratic Average: 29.42218589782715
Nearest Class Center Accuracy: 0.1136

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.009858124889433384
Inter Cos: 0.2638872265815735
Norm Quadratic Average: 41.615604400634766
Nearest Class Center Accuracy: 0.2665

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.01498414110392332
Inter Cos: 0.19859199225902557
Norm Quadratic Average: 21.07701873779297
Nearest Class Center Accuracy: 0.3936

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013921369798481464
Inter Cos: 0.1451607346534729
Norm Quadratic Average: 19.338041305541992
Nearest Class Center Accuracy: 0.5027

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.0137032987549901
Inter Cos: 0.1471678912639618
Norm Quadratic Average: 11.60519027709961
Nearest Class Center Accuracy: 0.584

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.013425947166979313
Inter Cos: 0.13664652407169342
Norm Quadratic Average: 11.901910781860352
Nearest Class Center Accuracy: 0.6126

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.022511065006256104
Inter Cos: 0.1997903436422348
Norm Quadratic Average: 8.653079986572266
Nearest Class Center Accuracy: 0.6087

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06514661759138107
Inter Cos: 0.3558013439178467
Norm Quadratic Average: 7.7069807052612305
Nearest Class Center Accuracy: 0.579

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 39.66019058227539
Linear Weight Rank: 4030
Intra Cos: 0.16064126789569855
Inter Cos: 0.4448072612285614
Norm Quadratic Average: 34.999473571777344
Nearest Class Center Accuracy: 0.5407

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 19.27256202697754
Linear Weight Rank: 3655
Intra Cos: 0.18327036499977112
Inter Cos: 0.4476925730705261
Norm Quadratic Average: 26.713224411010742
Nearest Class Center Accuracy: 0.5412

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 10.086735725402832
Linear Weight Rank: 98
Intra Cos: 0.18620312213897705
Inter Cos: 0.5070638060569763
Norm Quadratic Average: 26.6397647857666
Nearest Class Center Accuracy: 0.5369

Output Layer:
Intra Cos: 0.20816414058208466
Inter Cos: 0.6308198571205139
Norm Quadratic Average: 42.236724853515625
Nearest Class Center Accuracy: 0.5308

