Model save path: ./New_Models/bn_False_dataset_MNIST_epochs_100_lr_0.001_model_type_vgg11_rand_seed_265358_weight_decay_0.0001.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: 0.11120988428592682
Inter Cos: 0.12877337634563446
Norm Quadratic Average: 46.18827438354492
Nearest Class Center Accuracy: 0.823625

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.15731467306613922
Inter Cos: 0.16292478144168854
Norm Quadratic Average: 43.495880126953125
Nearest Class Center Accuracy: 0.81775

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17831699550151825
Inter Cos: 0.1774635910987854
Norm Quadratic Average: 56.838775634765625
Nearest Class Center Accuracy: 0.832875

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.19410006701946259
Inter Cos: 0.17811726033687592
Norm Quadratic Average: 38.248199462890625
Nearest Class Center Accuracy: 0.86775

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.220633864402771
Inter Cos: 0.19361579418182373
Norm Quadratic Average: 37.41901779174805
Nearest Class Center Accuracy: 0.911375

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.29078570008277893
Inter Cos: 0.1772182583808899
Norm Quadratic Average: 23.019773483276367
Nearest Class Center Accuracy: 0.95025

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.4126199781894684
Inter Cos: 0.22422832250595093
Norm Quadratic Average: 18.40076446533203
Nearest Class Center Accuracy: 0.981875

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.9010009765625
Linear Weight Rank: 4031
Intra Cos: 0.6369403004646301
Inter Cos: 0.26467934250831604
Norm Quadratic Average: 82.0873031616211
Nearest Class Center Accuracy: 0.998125

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.79297637939453
Linear Weight Rank: 3671
Intra Cos: 0.7321534156799316
Inter Cos: 0.2622162699699402
Norm Quadratic Average: 53.21525955200195
Nearest Class Center Accuracy: 0.999625

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.511108160018921
Linear Weight Rank: 10
Intra Cos: 0.774270236492157
Inter Cos: 0.2549761235713959
Norm Quadratic Average: 41.34283447265625
Nearest Class Center Accuracy: 0.99975

Output Layer:
Intra Cos: 0.8098517060279846
Inter Cos: 0.326836496591568
Norm Quadratic Average: 30.015758514404297
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.08962353925779462
Accuracy: 0.9785
NC1 Within Class Collapse: 1.6594083309173584
NC2 Equinorm: Features: 0.11336605995893478, Weights: 0.012336226180195808
NC2 Equiangle: Features: 0.24832486046685112, Weights: 0.09801279703776042
NC3 Self-Duality: 0.5603088140487671
NC4 NCC Mismatch: 0.009499999999999953

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: 0.1320953369140625
Inter Cos: 0.1453789323568344
Norm Quadratic Average: 45.32047653198242
Nearest Class Center Accuracy: 0.816

Layer 2: Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17060476541519165
Inter Cos: 0.19931083917617798
Norm Quadratic Average: 42.74152374267578
Nearest Class Center Accuracy: 0.818

Layer 3: Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.17614096403121948
Inter Cos: 0.21486064791679382
Norm Quadratic Average: 55.852115631103516
Nearest Class Center Accuracy: 0.8305

Layer 4: Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.1765315681695938
Inter Cos: 0.20874767005443573
Norm Quadratic Average: 37.56816864013672
Nearest Class Center Accuracy: 0.86

Layer 5: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.20105727016925812
Inter Cos: 0.22408369183540344
Norm Quadratic Average: 36.82310104370117
Nearest Class Center Accuracy: 0.8965

Layer 6: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.26198050379753113
Inter Cos: 0.18888014554977417
Norm Quadratic Average: 22.593353271484375
Nearest Class Center Accuracy: 0.9365

Layer 7: Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
Intra Cos: 0.3660288155078888
Inter Cos: 0.2145545482635498
Norm Quadratic Average: 18.002220153808594
Nearest Class Center Accuracy: 0.962

Layer 8: Linear(in_features=25088, out_features=4096, bias=True)
Linear Weight Norm: 100.9010009765625
Linear Weight Rank: 4031
Intra Cos: 0.5736044645309448
Inter Cos: 0.23889955878257751
Norm Quadratic Average: 79.77827453613281
Nearest Class Center Accuracy: 0.973

Layer 9: Linear(in_features=4096, out_features=4096, bias=True)
Linear Weight Norm: 40.79297637939453
Linear Weight Rank: 3671
Intra Cos: 0.6616440415382385
Inter Cos: 0.23908108472824097
Norm Quadratic Average: 51.607540130615234
Nearest Class Center Accuracy: 0.9785

Layer 10: Linear(in_features=4096, out_features=10, bias=True)
Linear Weight Norm: 2.511108160018921
Linear Weight Rank: 10
Intra Cos: 0.6981372237205505
Inter Cos: 0.2614855468273163
Norm Quadratic Average: 40.133522033691406
Nearest Class Center Accuracy: 0.979

Output Layer:
Intra Cos: 0.7230141162872314
Inter Cos: 0.3643953800201416
Norm Quadratic Average: 29.128875732421875
Nearest Class Center Accuracy: 0.979

