Model save path: /content/drive/MyDrive/Neural Collapse/New_Models/dataset_conic_model_depth_MLP_6_weight_decay_0.001.pth.tar
Training Set:
Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 6.0389275550842285
Intra Cos: 0.07988917827606201
Inter Cos: 0.0017584810266271234
Norm Quadratic Average: 4.001680850982666
Nearest Class Center Accuracy: 0.948875

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 4.933904647827148
Intra Cos: 0.18052344024181366
Inter Cos: 0.08822135627269745
Norm Quadratic Average: 2.034165143966675
Nearest Class Center Accuracy: 0.756375

Layer 2: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 2.1977834701538086
Intra Cos: 0.3553195297718048
Inter Cos: 0.02750988118350506
Norm Quadratic Average: 1.4714348316192627
Nearest Class Center Accuracy: 0.989

Layer 3: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 1.33322274684906
Intra Cos: 0.7769378423690796
Inter Cos: 0.07729647308588028
Norm Quadratic Average: 0.7955218553543091
Nearest Class Center Accuracy: 0.999875

Layer 4: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 1.346571922302246
Intra Cos: 0.9441219568252563
Inter Cos: -0.170746847987175
Norm Quadratic Average: 0.7265692949295044
Nearest Class Center Accuracy: 1.0

Layer 5: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.5953662395477295
Intra Cos: 0.968027651309967
Inter Cos: -0.22309815883636475
Norm Quadratic Average: 3.3839025497436523
Nearest Class Center Accuracy: 1.0

Output Layer:
Intra Cos: 0.9817231893539429
Inter Cos: -0.27028924226760864
Norm Quadratic Average: 6.95912504196167
Nearest Class Center Accuracy: 1.0

Test Set:
Average Loss: 0.06124145519733429
Accuracy: 0.9795
NC1 Within Class Collapse: 0.1829816699028015
NC2 Equinorm: Features: 0.006568723823875189, Weights: 0.02629077062010765
NC2 Equiangle: Features: 0.017969965934753418, Weights: 0.02876250445842743
NC3 Self-Duality: 0.011976875364780426
NC4 NCC Mismatch: 0.0

Layer 0: Linear(in_features=16, out_features=200, bias=True)
Linear Weight Norm: 6.0389275550842285
Intra Cos: 0.08033028244972229
Inter Cos: 0.003312897402793169
Norm Quadratic Average: 3.988335609436035
Nearest Class Center Accuracy: 0.9165

Layer 1: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 4.933904647827148
Intra Cos: 0.17775480449199677
Inter Cos: 0.07640241831541061
Norm Quadratic Average: 2.0417258739471436
Nearest Class Center Accuracy: 0.7725

Layer 2: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 2.1977834701538086
Intra Cos: 0.35165882110595703
Inter Cos: 0.031682346016168594
Norm Quadratic Average: 1.4605708122253418
Nearest Class Center Accuracy: 0.967

Layer 3: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 1.33322274684906
Intra Cos: 0.7389604449272156
Inter Cos: 0.09328535944223404
Norm Quadratic Average: 0.7932888269424438
Nearest Class Center Accuracy: 0.9795

Layer 4: Linear(in_features=200, out_features=200, bias=True)
Linear Weight Norm: 1.346571922302246
Intra Cos: 0.8828715085983276
Inter Cos: -0.13770237565040588
Norm Quadratic Average: 0.7196211814880371
Nearest Class Center Accuracy: 0.979

Layer 5: Linear(in_features=200, out_features=4, bias=True)
Linear Weight Norm: 3.5953662395477295
Intra Cos: 0.9064096212387085
Inter Cos: -0.29486149549484253
Norm Quadratic Average: 3.339080810546875
Nearest Class Center Accuracy: 0.9795

Output Layer:
Intra Cos: 0.928411066532135
Inter Cos: -0.2530354857444763
Norm Quadratic Average: 6.861930847167969
Nearest Class Center Accuracy: 0.9795

