diff --git a/docs/data-models.md b/docs/data-models.md index fde48d5..d55c4e5 100644 --- a/docs/data-models.md +++ b/docs/data-models.md @@ -6,7 +6,7 @@ The developed data models are listed here: | Name | Description | Specification | Python class | |------|-------------|---------------|--------------| -| Face | Store information about some inferred attributes about a Face | [schema.json](./DataModels/Face/schema.json) | [Face.py](../toolbox/DataModels/Face.py) -| InstanceSegmentation | Store information about a segmented object in an image | [schema.json](./DataModels/InstanceSegmentation/schema.json) | [InstanceSegmentation.py](../toolbox/DataModels/InstanceSegmentation.py) -| PersonKeyPoints | Store the position of different body parts within an image | [schema.json](./DataModels/PersonKeyPoints/schema.json) | [PersonKeyPoints.py](../toolbox/DataModels/PersonKeyPoints.py) -| Image | Stores information about an uploaded image | [schema.json](./DataModels/Image/schema.json) | [Image.py](../toolbox/DataModels/Image.py) \ No newline at end of file +| Face | Store information about some inferred attributes about a Face | [schema.json](./DataModels/Face/schema.json) | [Face.py](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/DataModels.html#module-DataModels.Face) +| InstanceSegmentation | Store information about a segmented object in an image | [schema.json](./DataModels/InstanceSegmentation/schema.json) | [InstanceSegmentation.py](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/DataModels.html#module-DataModels.InstanceSegmentation) +| PersonKeyPoints | Store the position of different body parts within an image | [schema.json](./DataModels/PersonKeyPoints/schema.json) | [PersonKeyPoints.py](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/DataModels.html#module-DataModels.PersonKeyPoints) +| Image | Stores information about an uploaded image | [schema.json](./DataModels/Image/schema.json) | [Image.py](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/DataModels.html#module-DataModels.Image) \ No newline at end of file diff --git a/docs/machine-learning-models.md b/docs/machine-learning-models.md index 095a187..b2cb23c 100644 --- a/docs/machine-learning-models.md +++ b/docs/machine-learning-models.md @@ -7,25 +7,25 @@ The output of the models is composed of [Toolbox Structures](./structures.md). ## Face analysis | Name | Description | Output | |------|-------------|--------| -| [age_gender](../toolbox/Models/age_gender/README.md) | Predict the age and gender of a face image | ([Gender](../toolbox/Structures/Gender.py), float) -| [emotions_hse](../toolbox/Models/emotions_hse/README.md) | Recognize 7 different emotions from a face image | [Emotion](/toolbox/Structures/Emotion.py) +| [age_gender](../toolbox/Models/age_gender/README.md) | Predict the age and gender of a face image | ([Gender](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/Structures.html#Structures.Gender.Gender), float) +| [emotions_hse](../toolbox/Models/emotions_hse/README.md) | Recognize 7 different emotions from a face image | [Emotion](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/Structures.html#module-Structures.Emotion) | [face_recognition_facenet](../toolbox/Models/face_recognition_facenet/README.md) | Perform face recognition tasks | (str, float) \| np.ndarray ## Object detection | Name | Description | Output | |------|-------------|--------| -| [face_detector_retinaface](../toolbox/Models/face_detector_retinaface/README.md) | Detect faces in images | [BoundingBox](/toolbox/Structures/BoundingBox.py) -| [face_detector_ultraface](../toolbox/Models/face_detector_ultraface/README.md) | Detect faces in images | [BoundingBox](/toolbox/Structures/BoundingBox.py) +| [face_detector_retinaface](../toolbox/Models/face_detector_retinaface/README.md) | Detect faces in images | [BoundingBox](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/Structures.html#module-Structures.BoundingBox) +| [face_detector_ultraface](../toolbox/Models/face_detector_ultraface/README.md) | Detect faces in images | [BoundingBox](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/Structures.html#module-Structures.BoundingBox) ## Instance segmentation | Name | Description | Output | |------|-------------|--------| -| [detectron2](../toolbox/Models/detectron2/README.md) | Perform instance segmentation of 80 different objects | [SegmentationMask](/toolbox/Structures/SegmentationMask.py) +| [detectron2](../toolbox/Models/detectron2/README.md) | Perform instance segmentation of 80 different objects | [SegmentationMask](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/Structures.html#module-Structures.SegmentationMask) ## Keypoints | Name | Description | Output | |------|-------------|--------| -| [detectron2](../toolbox/Models/detectron2/README.md) | Predict the position of 17 body key points | [COCOKeypoints](/toolbox/Structures/Keypoints.py) +| [detectron2](../toolbox/Models/detectron2/README.md) | Predict the position of 17 body key points | [COCOKeypoints](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/Structures.html#module-Structures.Keypoints) diff --git a/docs/structures.md b/docs/structures.md index e35660d..0056990 100644 --- a/docs/structures.md +++ b/docs/structures.md @@ -4,7 +4,7 @@ The Toolbox Structures are a set of Python Classes used to represent the output The following Structures are implemented: -## [Instance](https://github.com/CommuniCityProject/communicity_toolbox/blob/master/toolbox/Structures/Instance.py) +## [Instance](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/Structures.html#module-Structures.Instance) Structure similar to a Python ``dict``, used to aggregate the different outputs of a machine learning algorithm for each instance. e.g. A face detector algorithm will produce an ``Instance`` object for each detected face, storing inside it the bounding box and the detection confidence. @@ -20,7 +20,7 @@ print(dict(instance)) # > {'label': 'Car', 'confidence': 0.99} ``` -## [BoundingBox](https://github.com/CommuniCityProject/communicity_toolbox/blob/master/toolbox/Structures/BoundingBox.py) +## [BoundingBox](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/Structures.html#module-Structures.BoundingBox) Used to store the coordinates of a bounding box, that is a set of two points delimiting a rectangular area that encloses an object in an image. By default it uses the minimum and maximum x and y coordinates, which represents the top-left and bottom-right corner of the object inside the image. The coordinates of the bounding box are relative to the image size, ranging from ``0.`` to ``1.``. @@ -31,7 +31,7 @@ print(box, box.get_width(), box.get_height(), box.get_area()) # > BoundingBox(0.1,0.2,0.5,0.8) 0.4 0.6 0.24 ``` -## [Emotion](https://github.com/CommuniCityProject/communicity_toolbox/blob/master/toolbox/Structures/Emotion.py) +## [Emotion](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/Structures.html#module-Structures.Emotion) ``Enum`` class used to define the expression of a face. @@ -43,7 +43,7 @@ print(Emotion.HAPPINESS) # > HAPPINESS ``` -## [Gender](https://github.com/CommuniCityProject/communicity_toolbox/blob/master/toolbox/Structures/Gender.py) +## [Gender](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/Structures.html#module-Structures.Gender) ``Enum`` class used to define the gender of a person. @@ -55,7 +55,7 @@ print(Gender.FEMALE) # > FEMALE ``` -## [Image](https://github.com/CommuniCityProject/communicity_toolbox/blob/master/toolbox/Structures/Image.py) +## [Image](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/Structures.html#module-Structures.Image) Structure to store an image, allowing to load it from a local file or an URL. @@ -70,7 +70,7 @@ print(image.image.shape) # > (360, 640, 3) ``` -## [Keypoints](https://github.com/CommuniCityProject/communicity_toolbox/blob/master/toolbox/Structures/Keypoints.py) +## [Keypoints](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/Structures.html#module-Structures.Keypoints) Store a set of keypoints that represents the position of some body parts in an image. The coordinates are relative to the image size. @@ -99,7 +99,7 @@ print(keypoints.visible_keypoints) # 'right_ankle': [0.7277946288755803, 0.90788956211731, 0.4920530598870443]} ``` -## [SegmentationMask](https://github.com/CommuniCityProject/communicity_toolbox/blob/master/toolbox/Structures/SegmentationMask.py) +## [SegmentationMask](https://communicity-docs.readthedocs.io/en/latest/docs/toolbox/Structures.html#module-Structures.SegmentationMask) Represents a segmentation mask, that is a binary image defining the region occupied by an object in an image.