Add a new example and more

- Add an example of retraining all internal reider classifiers for GTA V dataset
- Rearrange some examples

docs/examples.rst

@@ -23,6 +23,7 @@ The examples below will help you make the most use of **pyppbox**. Before you tr
    examples/example_11
    examples/example_12
    examples/example_13
+   examples/example_14
 
 |
 

docs/examples/example_12.rst

@@ -1,14 +1,13 @@
-Example 12: Use a supported module directly
-===========================================
+Example 12: Train all the internal reider classifiers for GTA V dataset
+=======================================================================
 
-- **Description**: Use a supported detector/tracker/reider directly in your code.
+- **Description**: Use the standalone :func:`trainReIDClassifier()` to train and save a classifier .PKL files for GTA V dataset.
 - **Featuring**: 
-   - :py:class:`MyYOLOULT` | :py:class:`pyppbox.modules.detectors.yoloult.MyYOLOULT`
-   - :py:class:`DCFGYOLOULT` | :py:class:`pyppbox.config.myconfig.DCFGYOLOULT`
+   - :py:meth:`trainReIDClassifier` | :py:meth:`pyppbox.standalone.trainReIDClassifier`
 
 ℹ️ **Source code and input file(s)** -> `{pyppbox repo}/examples`_
 
 .. _{pyppbox repo}/examples: https://github.com/rathaumons/pyppbox/tree/main/examples
 
-.. literalinclude:: ../../examples/example_12_direct_module.py
+.. literalinclude:: ../../examples/example_12_retain_gta5_reid_classifiers.py
    :encoding: latin-1

docs/examples/example_13.rst

@@ -1,14 +1,14 @@
-Example 13: Use pyppbox in multithreading application
-=====================================================
+Example 13: Use a supported module directly
+===========================================
 
-- **Description**: Use a pyppbox in multithreading application.
+- **Description**: Use a supported detector/tracker/reider directly in your code.
 - **Featuring**: 
-   - :py:class:`MT` | :py:class:`pyppbox.ppb.mt.MT`
-   - :py:func:`visualizePeople` | :py:func:`pyppbox.utils.visualizetools.visualizePeople`
+   - :py:class:`MyYOLOULT` | :py:class:`pyppbox.modules.detectors.yoloult.MyYOLOULT`
+   - :py:class:`DCFGYOLOULT` | :py:class:`pyppbox.config.myconfig.DCFGYOLOULT`
 
 ℹ️ **Source code and input file(s)** -> `{pyppbox repo}/examples`_
 
 .. _{pyppbox repo}/examples: https://github.com/rathaumons/pyppbox/tree/main/examples
 
-.. literalinclude:: ../../examples/example_13_multithreading.py
+.. literalinclude:: ../../examples/example_13_direct_module.py
    :encoding: latin-1

docs/examples/example_14.rst

@@ -0,0 +1,14 @@
+Example 14: Use pyppbox in multithreading application
+=====================================================
+
+- **Description**: Use a pyppbox in multithreading application.
+- **Featuring**: 
+   - :py:class:`MT` | :py:class:`pyppbox.ppb.mt.MT`
+   - :py:func:`visualizePeople` | :py:func:`pyppbox.utils.visualizetools.visualizePeople`
+
+ℹ️ **Source code and input file(s)** -> `{pyppbox repo}/examples`_
+
+.. _{pyppbox repo}/examples: https://github.com/rathaumons/pyppbox/tree/main/examples
+
+.. literalinclude:: ../../examples/example_14_multithreading.py
+   :encoding: latin-1

examples/example_12_retain_gta5_reid_classifiers.py

@@ -0,0 +1,48 @@
+#################################################################################
+# Example of retraining all the internal reider classifiers for GTA V dataset
+#################################################################################
+
+import os
+import pyppbox
+from pyppbox.standalone import trainReIDClassifier
+
+
+pyppbox_root = os.path.dirname(pyppbox.__file__)
+
+gta5_osnet_ain_config = {
+    'ri_name': 'Torchreid', 
+    'classifier_pkl': f'{pyppbox_root}/data/modules/torchreid/classifier/gta5_osnet_ain_ms_d_c.pkl', 
+    'train_data': f'{pyppbox_root}/data/datasets/GTA_V_DATASET/body_128x256', 
+    'model_name': 'osnet_ain_x1_0', 
+    'model_path': f'{pyppbox_root}/data/modules/torchreid/models/torchreid/osnet_ain_ms_d_c.pth.tar', 
+    'min_confidence': 0.35, 
+    'device': 'cuda'
+}
+
+gta5_osnet_config = {
+    'ri_name': 'Torchreid', 
+    'classifier_pkl': f'{pyppbox_root}/data/modules/torchreid/classifier/gta5_osnet_ms_d_c.pkl', 
+    'train_data': f'{pyppbox_root}/data/datasets/GTA_V_DATASET/body_128x256', 
+    'model_name': 'osnet_x1_0', 
+    'model_path': f'{pyppbox_root}/data/modules/torchreid/models/torchreid/osnet_ms_d_c.pth.tar', 
+    'min_confidence': 0.35, 
+    'device': 'cuda'
+}
+
+gta5_facenet_config = {
+    'ri_name': 'FaceNet', 
+    'gpu_mem': 0.585, 
+    'model_det': f'{pyppbox_root}/data/modules/facenet/models/det', 
+    'model_file': f'{pyppbox_root}/data/modules/facenet/models/20180402-114759/20180402-114759.pb', 
+    'classifier_pkl': f'{pyppbox_root}/data/modules/facenet/classifier/gta5.pkl', 
+    'train_data': f'{pyppbox_root}/data/datasets/GTA_V_DATASET/face_182x182', 
+    'batch_size': 1000, 
+    'min_confidence': 0.75, 
+    'yl_h_calibration': [-125, 75], 
+    'yl_w_calibration': [-55, 55]
+}
+
+trainReIDClassifier(reider=gta5_osnet_ain_config)
+trainReIDClassifier(reider=gta5_osnet_config)
+trainReIDClassifier(reider=gta5_facenet_config)
+