Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/bn_False_dataset_mlp6_epochs_100_lr_0.001_model_depth_MLP_3_model_type_MLP_rand_seed_979323_weight_decay_0.01.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.442442417144775
Linear Weight Rank: 16
Intra Cos: 0.014583897776901722
Inter Cos: 0.004829857032746077
Norm Quadratic Average: 3.9931399822235107
Nearest Class Center Accuracy: 0.447

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.407490253448486
Linear Weight Rank: 179
Intra Cos: 0.017640799283981323
Inter Cos: 0.008209699764847755
Norm Quadratic Average: 3.2900850772857666
Nearest Class Center Accuracy: 0.473

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.1026926040649414
Linear Weight Rank: 4
Intra Cos: 0.07515105605125427
Inter Cos: 0.04088685289025307
Norm Quadratic Average: 1.422921895980835
Nearest Class Center Accuracy: 0.508875

Output Layer:
Intra Cos: 0.14204414188861847
Inter Cos: 0.09520795196294785
Norm Quadratic Average: 1.2761095762252808
Nearest Class Center Accuracy: 0.506125

Test Set:
Average Loss: 1.1632300605773926
Accuracy: 0.4995
NC1 Within Class Collapse: 19.607057571411133
NC2 Equinorm: Features: 0.11897111684083939, Weights: 0.017195304855704308
NC2 Equiangle: Features: 0.4528162082036336, Weights: 0.14052331447601318
NC3 Self-Duality: 0.2003483772277832
NC4 NCC Mismatch: 0.11950000000000005

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 5.442442417144775
Linear Weight Rank: 16
Intra Cos: 0.014108890667557716
Inter Cos: 0.005012288689613342
Norm Quadratic Average: 3.9761204719543457
Nearest Class Center Accuracy: 0.4485

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 5.407490253448486
Linear Weight Rank: 179
Intra Cos: 0.01752474531531334
Inter Cos: 0.007837362587451935
Norm Quadratic Average: 3.2722535133361816
Nearest Class Center Accuracy: 0.4785

Layer 2: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 2.1026926040649414
Linear Weight Rank: 4
Intra Cos: 0.06568188220262527
Inter Cos: 0.041150402277708054
Norm Quadratic Average: 1.4099621772766113
Nearest Class Center Accuracy: 0.4955

Output Layer:
Intra Cos: 0.12101709842681885
Inter Cos: 0.09365793317556381
Norm Quadratic Average: 1.2662497758865356
Nearest Class Center Accuracy: 0.4885

