Merge pull request #65 from PUTvision/model_zoo

New Model ZOO

README.md

@@ -20,6 +20,10 @@ Plugin for QGIS to perform map/image segmentation, regression and object detecti
 
 You can find the documentation [here](https://qgis-plugin-deepness.readthedocs.io/).
 
+## Deepness Model ZOO
+
+Check our example models in the [Model ZOO](./docs/source/main/model_zoo/MODEL_ZOO.md).
+
 ## Development
 
 - Install QGIS (the plugin was tested with QGIS 3.12)

docs/source/conf.py

@@ -68,6 +68,8 @@
     'sphinx.ext.intersphinx',
     'sphinx.ext.napoleon',
     'sphinxcontrib.youtube',
+    'm2r2',
+    'sphinx_rtd_size',
 ]
 
 MOCK_MODULES = ['future', 'qgis', 'osgeo', 'qgis.core', 'qgis.gui', 'qgis.utils', 'qgis.PyQt', 'qgis.PyQt.QtWidgets', 'qgis.PyQt.QtGui', 'qgis.PyQt.QtCore', 'PyQt5']
@@ -109,6 +111,7 @@
 #
 # html_theme = 'alabaster'
 html_theme = 'sphinx_rtd_theme'
+sphinx_rtd_size_width = "60%"
 
 html_theme_options = {
   'collapse_navigation': False,

docs/source/example/example_segmentation_landcover.rst

@@ -48,7 +48,7 @@ When model training is completed, export the model using the script below:
 Example inference
 =================
 
-Run QGIS, next add Google Eart map using :code:`QuickMapServices` plugin.
+Run QGIS, next add Google Earth map using :code:`QuickMapServices` plugin.
 
 .. image:: ../images/example_landcover_input_image.webp
 
@@ -72,4 +72,4 @@ After a few seconds, the results are available:
 
 * predicted mask with Google Earth background
 
-    .. image:: ../images/example_landcover_output_map.webp
+    .. image:: ../images/example_landcover_output_map.webp

docs/source/main/main_model_zoo.rst

@@ -1,37 +1 @@
-Sample Model ZOO
-================
-
-The `Model ZOO <https://chmura.put.poznan.pl/s/O69QZggRYprk3Ks>`_ is a collection of pre-trained, deep learning models in the ONNX format. It allows for an easy-to-use start with the plugin.
-
-
-===================
-Segmentation models
-===================
-
-+-----------------------------------------+-------------------------+----------------------------------------------------------------+
-| Task                                    |  Model                  |            ONNX Model                                          |
-+=========================================+=========================+================================================================+
-| Land Cover segmentation                 |  DeepLabV3+             |   `Link <#>`_                                                  |
-+-----------------------------------------+-------------------------+----------------------------------------------------------------+
-| Corn Field Damage Segmentation          |  UNet++                 |   `Link <https://chmura.put.poznan.pl/s/98zo9C5AdTK5ra4>`_     |
-+-----------------------------------------+-------------------------+----------------------------------------------------------------+
-
-=======================
-Object detection models
-=======================
-
-+-----------------------------------------+-------------------------+----------------------------------------+
-| Task                                    |  Model                  |            ONNX Model                  |
-+=========================================+=========================+========================================+
-| Airbus Planes Detection                 |  YOLOv7-tiny            |   `Link <#>`_                          |
-+--------------------+--------------------+-------------------------+----------------------------------------+
-| Airbus Oil Storage Detection            |  YOLOv5-m               |   `Link <#>`_                          |
-+--------------------+--------------------+-------------------------+----------------------------------------+
-
-=================
-Regression models
-=================
-
-.. note::
-
-    Documentation in progress: add example regression model
+.. mdinclude:: model_zoo/MODEL_ZOO.md

docs/source/main/model_zoo/MODEL_ZOO.md

@@ -0,0 +1,35 @@
+# Deepness Model ZOO
+
+The [Model ZOO](https://chmura.put.poznan.pl/s/2pJk4izRurzQwu3) is a collection of pre-trained, deep learning models in the ONNX format. It allows for an easy-to-use start with the plugin.
+
+## Segmentation models
+
+| Model name                                                                         | Input size | CM/PX | Description | Example image |
+|------------------------------------------------------------------------------------|---|---|---|---------------------------------------------------------|
+| [Corn Field Damage Segmentation](https://chmura.put.poznan.pl/s/abWFTVYSDIcncWs) | 512 | 3 | [PUT Vision](https://putvision.github.io/) model for Corn Field Damage Segmentation created on own dataset labeled by experts. We used the classical UNet++ model. It generates 3 outputs: healthy crop, damaged crop, and out-of-field area. | [Image](https://chmura.put.poznan.pl/s/i5WVmcfqPNdBTAQ) | 
+| [Land Cover Segmentation](https://chmura.put.poznan.pl/s/PnAFJw27uneROkV)          | 512 | 40 | The model is trained on the [LandCover.ai dataset](https://landcover.ai.linuxpolska.com/). It provides satellite images with 25 cm/px and 50 cm/px resolution. Annotation masks for the following classes are provided for the images: building (1), woodland (2), water(3), road(4). We use `DeepLabV3+` model with `tu-semnasnet_100` backend and `FocalDice` as a loss function. | [Image](https://chmura.put.poznan.pl/s/Xa29vnieNQTvSt5) |
+| [Roads Segmentation](https://chmura.put.poznan.pl/s/y6S3CmodPy1fYYz)            | 512 | 21 | The model segments the Google Earth satellite images into 'road' and 'not-road' classes. Model works best on wide car roads, crossroads and roundabouts.  | [Image](https://chmura.put.poznan.pl/s/rln6mpbjpsXWpKg) |
+
+## Regression models
+
+| Model name | Input size | CM/PX | Description | Example image |
+|---|---|---|---|---|
+|  |  |  |  |  |
+|  |  |  |  |  |
+
+## Object detection models
+
+| Model name | Input size | CM/PX | Description | Example image |
+|---|---|---|---|
+| [Airbus Planes Detection](https://chmura.put.poznan.pl/s/bBIJ5FDPgyQvJ49) | 256 | 70 | YOLOv7 tiny model for object detection on satellite images. Based on the [Airbus Aircraft Detection dataset](https://www.kaggle.com/datasets/airbusgeo/airbus-aircrafts-sample-dataset). | [Image](https://chmura.put.poznan.pl/s/VfLmcWhvWf0UJfI) |
+| [Airbus Oil Storage Detection](https://chmura.put.poznan.pl/s/gMundpKsYUC7sNb) | 512 | 150 | YOLOv5-m model for object detection on satellite images. Based on the [Airbus Oil Storage Detection dataset](https://www.kaggle.com/datasets/airbusgeo/airbus-oil-storage-detection-dataset). | [Image](https://chmura.put.poznan.pl/s/T3pwaKlbFDBB2C3) |
+
+## Contributing
+
+* PRs with models are welcome! Please follow the [general model information](https://qgis-plugin-deepness.readthedocs.io/en/latest/creators/creators_description_classes.html).
+
+* Use `MODEL_ZOO` tag in your PRs to make it easier to find them.
+
+* If you need, you can check [how to export the model to ONNX](https://qgis-plugin-deepness.readthedocs.io/en/latest/creators/creators_example_onnx_model.html).
+
+* And do not forget to [add metadata to the ONNX model](https://qgis-plugin-deepness.readthedocs.io/en/latest/creators/creators_add_metadata_to_model.html). You can host your model yourself or ask us to do it.

requirements_development.txt

@@ -13,4 +13,5 @@ sphinxcontrib-youtube
 sphinx-autodoc-typehints
 sphinx-autopackagesummary
 sphinx_rtd_theme
-
+m2r2
+sphinx-rtd-size