58 data mining (#65)

* updated model training and added kaggle set kaggle set has more than 5000 images but not every face from each image could be detected * feat: trained and evaluated different models. * feat: added models. * feat: added number of samples. * feat: added output. * feat: added titles to plots. * feat: added title to plots. * feat: added the analysis of the pyfeat classifier. * refactor: adapt to kaggle * ran pyfeat detector --------- Co-authored-by: LasseFrm <64502978+LasseFrm@users.noreply.github.com> Co-authored-by: Jurek Sander <44340639+sanderjk5@users.noreply.github.com>
Grutschus · Dec 18, 2023 · cb0b516 · cb0b516
1 parent 81cebe3
commit cb0b516
Show file tree

Hide file tree

Showing 24 changed files with 43,510 additions and 62 deletions.
diff --git a/.gitignore b/.gitignore
@@ -158,3 +158,7 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+
+
+# data
+model-training/data/
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -7,6 +7,7 @@ repos:
       - id: check-xml
       - id: check-yaml
       - id: check-added-large-files
+        args: ['--maxkb=10000']
       - id: trailing-whitespace
 
   - repo: https://github.com/astral-sh/ruff-pre-commit

diff --git a/.vscode/settings.json b/.vscode/settings.json
@@ -11,5 +11,5 @@
     "python.testing.unittestEnabled": false,
     "python.testing.pytestEnabled": true,
     "jupyter.debugJustMyCode": false,
-    "python.analysis.typeCheckingMode": "basic"
+    "python.analysis.typeCheckingMode": "off"
 }
diff --git a/model-training/analyse_pyfeat.ipynb b/model-training/analyse_pyfeat.ipynb
diff --git a/model-training/aus_combined.csv b/model-training/aus_combined.csv
diff --git a/model-training/aus_diffusion_fer.csv b/model-training/aus_diffusion_fer.csv
diff --git a/model-training/aus_kaggle_set.csv b/model-training/aus_kaggle_set.csv
diff --git a/model-training/best_model.pkl b/model-training/best_model.pkl
diff --git a/model-training/best_model_wo_pca.pkl b/model-training/best_model_wo_pca.pkl
diff --git a/model-training/data_analysis_and_preprocessing.ipynb b/model-training/data_analysis_and_preprocessing.ipynb
diff --git a/model-training/fer_label_encoder.pkl b/model-training/fer_label_encoder.pkl
diff --git a/model-training/fer_model.pkl b/model-training/fer_model.pkl
diff --git a/model-training/fer_scaler.pkl b/model-training/fer_scaler.pkl
diff --git a/model-training/model_training.ipynb b/model-training/model_training.ipynb
diff --git a/model-training/model_training_and_evaluation.ipynb b/model-training/model_training_and_evaluation.ipynb
diff --git a/model-training/nn_training_and_evaluation.ipynb b/model-training/nn_training_and_evaluation.ipynb
diff --git a/model-training/pca.pkl b/model-training/pca.pkl