Model save path: ./New_Models/bn_True_dataset_CIFAR100_epochs_200_lr_0.01_model_type_vgg11_rand_seed_979323_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: 0.022893190383911133
Inter Cos: 0.07011394202709198
Norm Quadratic Average: 29.326318740844727
Nearest Class Center Accuracy: 0.03258

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.026301061734557152
Inter Cos: 0.02695145085453987
Norm Quadratic Average: 41.011505126953125
Nearest Class Center Accuracy: 0.04834

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02191026322543621
Inter Cos: 0.0228088591247797
Norm Quadratic Average: 21.299999237060547
Nearest Class Center Accuracy: 0.06068

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.018039941787719727
Inter Cos: 0.01951661705970764
Norm Quadratic Average: 19.31016731262207
Nearest Class Center Accuracy: 0.06918

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025718096643686295
Inter Cos: 0.02255101501941681
Norm Quadratic Average: 11.620840072631836
Nearest Class Center Accuracy: 0.07866

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.030635837465524673
Inter Cos: 0.02872372604906559
Norm Quadratic Average: 11.878705024719238
Nearest Class Center Accuracy: 0.08386

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.07263917475938797
Inter Cos: 0.05365132540464401
Norm Quadratic Average: 8.79195785522461
Nearest Class Center Accuracy: 0.09438

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26508277654647827
Inter Cos: 0.12855307757854462
Norm Quadratic Average: 8.151090621948242
Nearest Class Center Accuracy: 0.09974

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 39.67460250854492
Linear Weight Rank: 4030
Intra Cos: 0.6134461760520935
Inter Cos: 0.20979931950569153
Norm Quadratic Average: 39.73659133911133
Nearest Class Center Accuracy: 0.1

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 19.358566284179688
Linear Weight Rank: 3655
Intra Cos: 0.7858433127403259
Inter Cos: 0.2912009358406067
Norm Quadratic Average: 32.43440628051758
Nearest Class Center Accuracy: 0.1

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 10.161314010620117
Linear Weight Rank: 98
Intra Cos: 0.839133083820343
Inter Cos: 0.31720858812332153
Norm Quadratic Average: 32.911155700683594
Nearest Class Center Accuracy: 0.1

Output Layer:
Intra Cos: 0.9003931879997253
Inter Cos: 0.43745818734169006
Norm Quadratic Average: 52.28546905517578
Nearest Class Center Accuracy: 0.1

Test Set:
Average Loss: 2.8934952724456786
Accuracy: 0.5369
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.27465203404426575, Weights: 0.035493284463882446
NC2 Equiangle: Features: 0.17058832958491163, Weights: 0.09785028014520201
NC3 Self-Duality: 0.46984729170799255
NC4 NCC Mismatch: 0.15649999999999997

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.006621268577873707
Inter Cos: 0.4067547619342804
Norm Quadratic Average: 29.42218780517578
Nearest Class Center Accuracy: 0.1136

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.012780365534126759
Inter Cos: 0.25610241293907166
Norm Quadratic Average: 41.30317687988281
Nearest Class Center Accuracy: 0.2632

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.015392248518764973
Inter Cos: 0.2033466398715973
Norm Quadratic Average: 21.466306686401367
Nearest Class Center Accuracy: 0.3927

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.014126273803412914
Inter Cos: 0.15006563067436218
Norm Quadratic Average: 19.41179656982422
Nearest Class Center Accuracy: 0.5032

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.014932001940906048
Inter Cos: 0.14391805231571198
Norm Quadratic Average: 11.65551471710205
Nearest Class Center Accuracy: 0.5884

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.015020920895040035
Inter Cos: 0.12504927814006805
Norm Quadratic Average: 11.865157127380371
Nearest Class Center Accuracy: 0.6219

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.024617813527584076
Inter Cos: 0.18133659660816193
Norm Quadratic Average: 8.697417259216309
Nearest Class Center Accuracy: 0.6148

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.06612234562635422
Inter Cos: 0.3587513566017151
Norm Quadratic Average: 7.710737705230713
Nearest Class Center Accuracy: 0.5729

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 39.67460250854492
Linear Weight Rank: 4030
Intra Cos: 0.16768214106559753
Inter Cos: 0.48094967007637024
Norm Quadratic Average: 34.22526931762695
Nearest Class Center Accuracy: 0.5373

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 19.358566284179688
Linear Weight Rank: 3655
Intra Cos: 0.19541001319885254
Inter Cos: 0.49200698733329773
Norm Quadratic Average: 26.31633186340332
Nearest Class Center Accuracy: 0.5381

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 10.161314010620117
Linear Weight Rank: 98
Intra Cos: 0.19783982634544373
Inter Cos: 0.5508692860603333
Norm Quadratic Average: 26.493011474609375
Nearest Class Center Accuracy: 0.5363

Output Layer:
Intra Cos: 0.21503432095050812
Inter Cos: 0.6825990676879883
Norm Quadratic Average: 42.259700775146484
Nearest Class Center Accuracy: 0.5324

