Model save path: ./New_Models/bn_False_dataset_CIFAR100_epochs_200_lr_0.01_model_type_vgg11_rand_seed_314159_test_samples_None_train_samples_None_weight_decay_0.0001.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: 29.326322555541992
Nearest Class Center Accuracy: 0.03258

Layer 1: Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.035960860550403595
Inter Cos: 0.03247431293129921
Norm Quadratic Average: 43.306522369384766
Nearest Class Center Accuracy: 0.04646

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03304215148091316
Inter Cos: 0.03296055644750595
Norm Quadratic Average: 57.17850875854492
Nearest Class Center Accuracy: 0.05664

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.025240622460842133
Inter Cos: 0.026106616482138634
Norm Quadratic Average: 95.66764831542969
Nearest Class Center Accuracy: 0.06402

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03061923384666443
Inter Cos: 0.023729143664240837
Norm Quadratic Average: 73.39065551757812
Nearest Class Center Accuracy: 0.07202

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.029884368181228638
Inter Cos: 0.023715687915682793
Norm Quadratic Average: 69.65618133544922
Nearest Class Center Accuracy: 0.07558

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.05956443026661873
Inter Cos: 0.03692324087023735
Norm Quadratic Average: 33.34928894042969
Nearest Class Center Accuracy: 0.0872

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.16565203666687012
Inter Cos: 0.09230605512857437
Norm Quadratic Average: 18.367826461791992
Nearest Class Center Accuracy: 0.09694

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 74.58790588378906
Linear Weight Rank: 4031
Intra Cos: 0.5204800963401794
Inter Cos: 0.18620248138904572
Norm Quadratic Average: 64.97410583496094
Nearest Class Center Accuracy: 0.09978

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 33.29438400268555
Linear Weight Rank: 3664
Intra Cos: 0.6863663792610168
Inter Cos: 0.20095734298229218
Norm Quadratic Average: 46.865570068359375
Nearest Class Center Accuracy: 0.09996

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 13.691514015197754
Linear Weight Rank: 98
Intra Cos: 0.770088255405426
Inter Cos: 0.2188364416360855
Norm Quadratic Average: 39.83172607421875
Nearest Class Center Accuracy: 0.1

Output Layer:
Intra Cos: 0.8599584102630615
Inter Cos: 0.426309734582901
Norm Quadratic Average: 70.79571533203125
Nearest Class Center Accuracy: 0.1

Test Set:
Average Loss: 4.027653266906738
Accuracy: 0.4704
NC1 Within Class Collapse: nan
NC2 Equinorm: Features: 0.4045630693435669, Weights: 0.028056442737579346
NC2 Equiangle: Features: 0.14942513514046718, Weights: 0.09800926747948233
NC3 Self-Duality: 0.6709535717964172
NC4 NCC Mismatch: 0.2237

Layer 0: Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.006621268577873707
Inter Cos: 0.4067547917366028
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: 0.01588037982583046
Inter Cos: 0.24069666862487793
Norm Quadratic Average: 43.58434295654297
Nearest Class Center Accuracy: 0.2402

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.02020202949643135
Inter Cos: 0.22820159792900085
Norm Quadratic Average: 57.621639251708984
Nearest Class Center Accuracy: 0.3279

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.016720909625291824
Inter Cos: 0.17788401246070862
Norm Quadratic Average: 96.43890380859375
Nearest Class Center Accuracy: 0.4141

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.017160579562187195
Inter Cos: 0.17358742654323578
Norm Quadratic Average: 73.9797134399414
Nearest Class Center Accuracy: 0.499

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.016497019678354263
Inter Cos: 0.1260642558336258
Norm Quadratic Average: 69.81380462646484
Nearest Class Center Accuracy: 0.5385

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.020669281482696533
Inter Cos: 0.18630415201187134
Norm Quadratic Average: 32.70357894897461
Nearest Class Center Accuracy: 0.5378

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.03865804150700569
Inter Cos: 0.2520020604133606
Norm Quadratic Average: 17.022706985473633
Nearest Class Center Accuracy: 0.5147

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 74.58790588378906
Linear Weight Rank: 4031
Intra Cos: 0.09858249872922897
Inter Cos: 0.35733726620674133
Norm Quadratic Average: 53.33853530883789
Nearest Class Center Accuracy: 0.4664

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 33.29438400268555
Linear Weight Rank: 3664
Intra Cos: 0.12925145030021667
Inter Cos: 0.363802969455719
Norm Quadratic Average: 36.18183898925781
Nearest Class Center Accuracy: 0.4618

Layer 10: Linear(in_features=4096, out_features=100, bias=True)
Linear Weight Norm: 13.691514015197754
Linear Weight Rank: 98
Intra Cos: 0.14549033343791962
Inter Cos: 0.45396745204925537
Norm Quadratic Average: 30.018192291259766
Nearest Class Center Accuracy: 0.4611

Output Layer:
Intra Cos: 0.143315851688385
Inter Cos: 0.6973426342010498
Norm Quadratic Average: 52.8800048828125
Nearest Class Center Accuracy: 0.4562

