Upload folder using huggingface_hub

README.md

@@ -1,19 +1,3 @@
----
-tags:
-- gradio-custom-component
-- gradio-template-Image
-- bounding box
-- annotator
-- annotate
-- boxes
-title: gradio_image_annotation V0.3.1
-colorFrom: yellow
-colorTo: green
-sdk: docker
-pinned: false
-license: apache-2.0
-short_description: A Gradio component for image annotation
----
 
 # `gradio_image_annotation`
 <a href="https://pypi.org/project/gradio_image_annotation/" target="_blank"><img alt="PyPI - Version" src="https://img.shields.io/pypi/v/gradio_image_annotation"></a>  
@@ -22,6 +6,15 @@ A Gradio component that can be used to annotate images with bounding boxes.
 
 ![Demo preview](images/demo.png)
 
+## Keyboard Shortcuts:
+- `C`: Create mode
+- `D`: Drag mode
+- `E`: Edit selected box (same as double-click a box)
+- `Delete`: Remove selected box
+- `Space`: Reset view (zoom/pan)
+- `Enter`: Confirm modal dialog
+- `Escape`: Cancel/close modal dialog
+
 ## Installation
 
 ```bash
@@ -126,6 +119,17 @@ with gr.Blocks() as demo:
         button_crop.click(crop, annotator_crop, image_crop)
 
         gr.Examples(examples_crop, annotator_crop)
+    
+    with gr.Accordion("Keyboard Shortcuts"):
+        gr.Markdown("""
+        - ``C``: Create mode
+        - ``D``: Drag mode
+        - ``E``: Edit selected box (same as double-click a box)
+        - ``Delete``: Remove selected box
+        - ``Space``: Reset view (zoom/pan)
+        - ``Enter``: Confirm modal dialog
+        - ``Escape``: Cancel/close modal dialog
+        """)
 
 if __name__ == "__main__":
     demo.launch()
@@ -558,6 +562,19 @@ bool | None
 <td align="left"><code>False</code></td>
 <td align="left">If True, the first item in label_list will be used as the default label when creating boxes.</td>
 </tr>
+
+<tr>
+<td align="left"><code>enable_keyboard_shortcuts</code></td>
+<td align="left" style="width: 25%;">
+
+```python
+bool
+```
+
+</td>
+<td align="left"><code>True</code></td>
+<td align="left">If True, the component will respond to keyboard events.</td>
+</tr>
 </tbody></table>
 
 

app.py

@@ -94,5 +94,16 @@ with gr.Blocks() as demo:
 
         gr.Examples(examples_crop, annotator_crop)
 
+    with gr.Accordion("Keyboard Shortcuts"):
+        gr.Markdown("""
+        - ``C``: Create mode
+        - ``D``: Drag mode
+        - ``E``: Edit selected box (same as double-click a box)
+        - ``Delete``: Remove selected box
+        - ``Space``: Reset view (zoom/pan)
+        - ``Enter``: Confirm modal dialog
+        - ``Escape``: Cancel/close modal dialog
+        """)
+
 if __name__ == "__main__":
     demo.launch()

space.py

@@ -3,7 +3,7 @@ import gradio as gr
 from app import demo as app
 import os
 
-_docs = {'image_annotator': {'description': 'Creates a component to annotate images with bounding boxes. The bounding boxes can be created and edited by the user or be passed by code.\nIt is also possible to predefine a set of valid classes and colors.', 'members': {'__init__': {'value': {'type': 'dict | None', 'default': 'None', 'description': "A dict or None. The dictionary must contain a key 'image' with either an URL to an image, a numpy image or a PIL image. Optionally it may contain a key 'boxes' with a list of boxes. Each box must be a dict wit the keys: 'xmin', 'ymin', 'xmax' and 'ymax' with the absolute image coordinates of the box. Optionally can also include the keys 'label' and 'color' describing the label and color of the box. Color must be a tuple of RGB values (e.g. `(255,255,255)`). Optionally can also include the keys 'orientation' with a integer between 0 and 3, describing the number of times the image is rotated by 90 degrees in frontend, the rotation is clockwise."}, 'boxes_alpha': {'type': 'float | None', 'default': 'None', 'description': 'Opacity of the bounding boxes 0 and 1.'}, 'label_list': {'type': 'list[str] | None', 'default': 'None', 'description': 'List of valid labels.'}, 'label_colors': {'type': 'list[str] | None', 'default': 'None', 'description': 'Optional list of colors for each label when `label_list` is used. Colors must be a tuple of RGB values (e.g. `(255,255,255)`).'}, 'box_min_size': {'type': 'int | None', 'default': 'None', 'description': 'Minimum valid bounding box size.'}, 'handle_size': {'type': 'int | None', 'default': 'None', 'description': 'Size of the bounding box resize handles.'}, 'box_thickness': {'type': 'int | None', 'default': 'None', 'description': 'Thickness of the bounding box outline.'}, 'box_selected_thickness': {'type': 'int | None', 'default': 'None', 'description': 'Thickness of the bounding box outline when it is selected.'}, 'disable_edit_boxes': {'type': 'bool | None', 'default': 'None', 'description': 'Disables the ability to set and edit the label and color of the boxes.'}, 'single_box': {'type': 'bool', 'default': 'False', 'description': 'If True, at most one box can be drawn.'}, 'height': {'type': 'int | str | None', 'default': 'None', 'description': 'The height of the displayed image, specified in pixels if a number is passed, or in CSS units if a string is passed.'}, 'width': {'type': 'int | str | None', 'default': 'None', 'description': 'The width of the displayed image, specified in pixels if a number is passed, or in CSS units if a string is passed.'}, 'image_mode': {'type': '"1"\n    | "L"\n    | "P"\n    | "RGB"\n    | "RGBA"\n    | "CMYK"\n    | "YCbCr"\n    | "LAB"\n    | "HSV"\n    | "I"\n    | "F"', 'default': '"RGB"', 'description': '"RGB" if color, or "L" if black and white. See https://pillow.readthedocs.io/en/stable/handbook/concepts.html for other supported image modes and their meaning.'}, 'sources': {'type': 'list["upload" | "webcam" | "clipboard"] | None', 'default': '["upload", "webcam", "clipboard"]', 'description': 'List of sources for the image. "upload" creates a box where user can drop an image file, "webcam" allows user to take snapshot from their webcam, "clipboard" allows users to paste an image from the clipboard. If None, defaults to ["upload", "webcam", "clipboard"].'}, 'image_type': {'type': '"numpy" | "pil" | "filepath"', 'default': '"numpy"', 'description': 'The format the image is converted before being passed into the prediction function. "numpy" converts the image to a numpy array with shape (height, width, 3) and values from 0 to 255, "pil" converts the image to a PIL image object, "filepath" passes a str path to a temporary file containing the image. If the image is SVG, the `type` is ignored and the filepath of the SVG is returned.'}, 'label': {'type': 'str | None', 'default': 'None', 'description': 'The label for this component. Appears above the component and is also used as the header if there are a table of examples for this component. If None and used in a `gr.Interface`, the label will be the name of the parameter this component is assigned to.'}, 'container': {'type': 'bool', 'default': 'True', 'description': 'If True, will place the component in a container - providing some extra padding around the border.'}, 'scale': {'type': 'int | None', 'default': 'None', 'description': 'relative size compared to adjacent Components. For example if Components A and B are in a Row, and A has scale=2, and B has scale=1, A will be twice as wide as B. Should be an integer. scale applies in Rows, and to top-level Components in Blocks where fill_height=True.'}, 'min_width': {'type': 'int', 'default': '160', 'description': 'minimum pixel width, will wrap if not sufficient screen space to satisfy this value. If a certain scale value results in this Component being narrower than min_width, the min_width parameter will be respected first.'}, 'interactive': {'type': 'bool | None', 'default': 'True', 'description': 'if True, will allow users to upload and annotate an image; if False, can only be used to display annotated images.'}, 'visible': {'type': 'bool', 'default': 'True', 'description': 'If False, component will be hidden.'}, 'elem_id': {'type': 'str | None', 'default': 'None', 'description': 'An optional string that is assigned as the id of this component in the HTML DOM. Can be used for targeting CSS styles.'}, 'elem_classes': {'type': 'list[str] | str | None', 'default': 'None', 'description': 'An optional list of strings that are assigned as the classes of this component in the HTML DOM. Can be used for targeting CSS styles.'}, 'render': {'type': 'bool', 'default': 'True', 'description': 'If False, component will not render be rendered in the Blocks context. Should be used if the intention is to assign event listeners now but render the component later.'}, 'show_label': {'type': 'bool | None', 'default': 'None', 'description': 'if True, will display label.'}, 'show_download_button': {'type': 'bool', 'default': 'True', 'description': 'If True, will show a button to download the image.'}, 'show_share_button': {'type': 'bool | None', 'default': 'None', 'description': 'If True, will show a share icon in the corner of the component that allows user to share outputs to Hugging Face Spaces Discussions. If False, icon does not appear. If set to None (default behavior), then the icon appears if this Gradio app is launched on Spaces, but not otherwise.'}, 'show_clear_button': {'type': 'bool | None', 'default': 'True', 'description': 'If True, will show a button to clear the current image.'}, 'show_remove_button': {'type': 'bool | None', 'default': 'None', 'description': 'If True, will show a button to remove the selected bounding box.'}, 'handles_cursor': {'type': 'bool | None', 'default': 'True', 'description': 'If True, the cursor will change when hovering over box handles in drag mode. Can be CPU-intensive.'}, 'use_default_label': {'type': 'bool | None', 'default': 'False', 'description': 'If True, the first item in label_list will be used as the default label when creating boxes.'}}, 'postprocess': {'value': {'type': 'AnnotatedImageValue | None', 'description': 'A dict with an image and an optional list of boxes or None.'}}, 'preprocess': {'return': {'type': 'AnnotatedImageValue | None', 'description': 'A dict with the image and boxes or None.'}, 'value': None}}, 'events': {'clear': {'type': None, 'default': None, 'description': 'This listener is triggered when the user clears the image_annotator using the clear button for the component.'}, 'change': {'type': None, 'default': None, 'description': 'Triggered when the value of the image_annotator changes either because of user input (e.g. a user types in a textbox) OR because of a function update (e.g. an image receives a value from the output of an event trigger). See `.input()` for a listener that is only triggered by user input.'}, 'upload': {'type': None, 'default': None, 'description': 'This listener is triggered when the user uploads a file into the image_annotator.'}}}, '__meta__': {'additional_interfaces': {'AnnotatedImageValue': {'source': 'class AnnotatedImageValue(TypedDict):\n    image: Optional[np.ndarray | PIL.Image.Image | str]\n    boxes: Optional[List[dict]]\n    orientation: Optional[int]'}}, 'user_fn_refs': {'image_annotator': ['AnnotatedImageValue']}}}
+_docs = {'image_annotator': {'description': 'Creates a component to annotate images with bounding boxes. The bounding boxes can be created and edited by the user or be passed by code.\nIt is also possible to predefine a set of valid classes and colors.', 'members': {'__init__': {'value': {'type': 'dict | None', 'default': 'None', 'description': "A dict or None. The dictionary must contain a key 'image' with either an URL to an image, a numpy image or a PIL image. Optionally it may contain a key 'boxes' with a list of boxes. Each box must be a dict wit the keys: 'xmin', 'ymin', 'xmax' and 'ymax' with the absolute image coordinates of the box. Optionally can also include the keys 'label' and 'color' describing the label and color of the box. Color must be a tuple of RGB values (e.g. `(255,255,255)`). Optionally can also include the keys 'orientation' with a integer between 0 and 3, describing the number of times the image is rotated by 90 degrees in frontend, the rotation is clockwise."}, 'boxes_alpha': {'type': 'float | None', 'default': 'None', 'description': 'Opacity of the bounding boxes 0 and 1.'}, 'label_list': {'type': 'list[str] | None', 'default': 'None', 'description': 'List of valid labels.'}, 'label_colors': {'type': 'list[str] | None', 'default': 'None', 'description': 'Optional list of colors for each label when `label_list` is used. Colors must be a tuple of RGB values (e.g. `(255,255,255)`).'}, 'box_min_size': {'type': 'int | None', 'default': 'None', 'description': 'Minimum valid bounding box size.'}, 'handle_size': {'type': 'int | None', 'default': 'None', 'description': 'Size of the bounding box resize handles.'}, 'box_thickness': {'type': 'int | None', 'default': 'None', 'description': 'Thickness of the bounding box outline.'}, 'box_selected_thickness': {'type': 'int | None', 'default': 'None', 'description': 'Thickness of the bounding box outline when it is selected.'}, 'disable_edit_boxes': {'type': 'bool | None', 'default': 'None', 'description': 'Disables the ability to set and edit the label and color of the boxes.'}, 'single_box': {'type': 'bool', 'default': 'False', 'description': 'If True, at most one box can be drawn.'}, 'height': {'type': 'int | str | None', 'default': 'None', 'description': 'The height of the displayed image, specified in pixels if a number is passed, or in CSS units if a string is passed.'}, 'width': {'type': 'int | str | None', 'default': 'None', 'description': 'The width of the displayed image, specified in pixels if a number is passed, or in CSS units if a string is passed.'}, 'image_mode': {'type': '"1"\n    | "L"\n    | "P"\n    | "RGB"\n    | "RGBA"\n    | "CMYK"\n    | "YCbCr"\n    | "LAB"\n    | "HSV"\n    | "I"\n    | "F"', 'default': '"RGB"', 'description': '"RGB" if color, or "L" if black and white. See https://pillow.readthedocs.io/en/stable/handbook/concepts.html for other supported image modes and their meaning.'}, 'sources': {'type': 'list["upload" | "webcam" | "clipboard"] | None', 'default': '["upload", "webcam", "clipboard"]', 'description': 'List of sources for the image. "upload" creates a box where user can drop an image file, "webcam" allows user to take snapshot from their webcam, "clipboard" allows users to paste an image from the clipboard. If None, defaults to ["upload", "webcam", "clipboard"].'}, 'image_type': {'type': '"numpy" | "pil" | "filepath"', 'default': '"numpy"', 'description': 'The format the image is converted before being passed into the prediction function. "numpy" converts the image to a numpy array with shape (height, width, 3) and values from 0 to 255, "pil" converts the image to a PIL image object, "filepath" passes a str path to a temporary file containing the image. If the image is SVG, the `type` is ignored and the filepath of the SVG is returned.'}, 'label': {'type': 'str | None', 'default': 'None', 'description': 'The label for this component. Appears above the component and is also used as the header if there are a table of examples for this component. If None and used in a `gr.Interface`, the label will be the name of the parameter this component is assigned to.'}, 'container': {'type': 'bool', 'default': 'True', 'description': 'If True, will place the component in a container - providing some extra padding around the border.'}, 'scale': {'type': 'int | None', 'default': 'None', 'description': 'relative size compared to adjacent Components. For example if Components A and B are in a Row, and A has scale=2, and B has scale=1, A will be twice as wide as B. Should be an integer. scale applies in Rows, and to top-level Components in Blocks where fill_height=True.'}, 'min_width': {'type': 'int', 'default': '160', 'description': 'minimum pixel width, will wrap if not sufficient screen space to satisfy this value. If a certain scale value results in this Component being narrower than min_width, the min_width parameter will be respected first.'}, 'interactive': {'type': 'bool | None', 'default': 'True', 'description': 'if True, will allow users to upload and annotate an image; if False, can only be used to display annotated images.'}, 'visible': {'type': 'bool', 'default': 'True', 'description': 'If False, component will be hidden.'}, 'elem_id': {'type': 'str | None', 'default': 'None', 'description': 'An optional string that is assigned as the id of this component in the HTML DOM. Can be used for targeting CSS styles.'}, 'elem_classes': {'type': 'list[str] | str | None', 'default': 'None', 'description': 'An optional list of strings that are assigned as the classes of this component in the HTML DOM. Can be used for targeting CSS styles.'}, 'render': {'type': 'bool', 'default': 'True', 'description': 'If False, component will not render be rendered in the Blocks context. Should be used if the intention is to assign event listeners now but render the component later.'}, 'show_label': {'type': 'bool | None', 'default': 'None', 'description': 'if True, will display label.'}, 'show_download_button': {'type': 'bool', 'default': 'True', 'description': 'If True, will show a button to download the image.'}, 'show_share_button': {'type': 'bool | None', 'default': 'None', 'description': 'If True, will show a share icon in the corner of the component that allows user to share outputs to Hugging Face Spaces Discussions. If False, icon does not appear. If set to None (default behavior), then the icon appears if this Gradio app is launched on Spaces, but not otherwise.'}, 'show_clear_button': {'type': 'bool | None', 'default': 'True', 'description': 'If True, will show a button to clear the current image.'}, 'show_remove_button': {'type': 'bool | None', 'default': 'None', 'description': 'If True, will show a button to remove the selected bounding box.'}, 'handles_cursor': {'type': 'bool | None', 'default': 'True', 'description': 'If True, the cursor will change when hovering over box handles in drag mode. Can be CPU-intensive.'}, 'use_default_label': {'type': 'bool | None', 'default': 'False', 'description': 'If True, the first item in label_list will be used as the default label when creating boxes.'}, 'enable_keyboard_shortcuts': {'type': 'bool', 'default': 'True', 'description': 'If True, the component will respond to keyboard events.'}}, 'postprocess': {'value': {'type': 'AnnotatedImageValue | None', 'description': 'A dict with an image and an optional list of boxes or None.'}}, 'preprocess': {'return': {'type': 'AnnotatedImageValue | None', 'description': 'A dict with the image and boxes or None.'}, 'value': None}}, 'events': {'clear': {'type': None, 'default': None, 'description': 'This listener is triggered when the user clears the image_annotator using the clear button for the component.'}, 'change': {'type': None, 'default': None, 'description': 'Triggered when the value of the image_annotator changes either because of user input (e.g. a user types in a textbox) OR because of a function update (e.g. an image receives a value from the output of an event trigger). See `.input()` for a listener that is only triggered by user input.'}, 'upload': {'type': None, 'default': None, 'description': 'This listener is triggered when the user uploads a file into the image_annotator.'}}}, '__meta__': {'additional_interfaces': {'AnnotatedImageValue': {'source': 'class AnnotatedImageValue(TypedDict):\n    image: Optional[np.ndarray | PIL.Image.Image | str]\n    boxes: Optional[List[dict]]\n    orientation: Optional[int]'}}, 'user_fn_refs': {'image_annotator': ['AnnotatedImageValue']}}}
 
 abs_path = os.path.join(os.path.dirname(__file__), "css.css")
 
@@ -133,6 +133,17 @@ with gr.Blocks() as demo:
         button_crop.click(crop, annotator_crop, image_crop)
 
         gr.Examples(examples_crop, annotator_crop)
+    
+    with gr.Accordion("Keyboard Shortcuts"):
+        gr.Markdown(\"\"\"
+        - ``C``: Create mode
+        - ``D``: Drag mode
+        - ``E``: Edit selected box (same as double-click a box)
+        - ``Delete``: Remove selected box
+        - ``Space``: Reset view (zoom/pan)
+        - ``Enter``: Confirm modal dialog
+        - ``Escape``: Cancel/close modal dialog
+        \"\"\")
 
 if __name__ == "__main__":
     demo.launch()

src/README.md

@@ -6,6 +6,15 @@ A Gradio component that can be used to annotate images with bounding boxes.
 
 ![Demo preview](images/demo.png)
 
+## Keyboard Shortcuts:
+- `C`: Create mode
+- `D`: Drag mode
+- `E`: Edit selected box (same as double-click a box)
+- `Delete`: Remove selected box
+- `Space`: Reset view (zoom/pan)
+- `Enter`: Confirm modal dialog
+- `Escape`: Cancel/close modal dialog
+
 ## Installation
 
 ```bash
@@ -110,6 +119,17 @@ with gr.Blocks() as demo:
         button_crop.click(crop, annotator_crop, image_crop)
 
         gr.Examples(examples_crop, annotator_crop)
+    
+    with gr.Accordion("Keyboard Shortcuts"):
+        gr.Markdown("""
+        - ``C``: Create mode
+        - ``D``: Drag mode
+        - ``E``: Edit selected box (same as double-click a box)
+        - ``Delete``: Remove selected box
+        - ``Space``: Reset view (zoom/pan)
+        - ``Enter``: Confirm modal dialog
+        - ``Escape``: Cancel/close modal dialog
+        """)
 
 if __name__ == "__main__":
     demo.launch()
@@ -542,6 +562,19 @@ bool | None
 <td align="left"><code>False</code></td>
 <td align="left">If True, the first item in label_list will be used as the default label when creating boxes.</td>
 </tr>
+
+<tr>
+<td align="left"><code>enable_keyboard_shortcuts</code></td>
+<td align="left" style="width: 25%;">
+
+```python
+bool
+```
+
+</td>
+<td align="left"><code>True</code></td>
+<td align="left">If True, the component will respond to keyboard events.</td>
+</tr>
 </tbody></table>
 
 

src/backend/gradio_image_annotation/image_annotator.py

@@ -89,6 +89,7 @@ class image_annotator(Component):
         show_remove_button: bool | None = None,
         handles_cursor: bool | None = True,
         use_default_label: bool | None = False,
+        enable_keyboard_shortcuts: bool = True, 
     ):
         """
         Parameters:
@@ -123,6 +124,7 @@ class image_annotator(Component):
             show_remove_button: If True, will show a button to remove the selected bounding box.
             handles_cursor: If True, the cursor will change when hovering over box handles in drag mode. Can be CPU-intensive.
             use_default_label: If True, the first item in label_list will be used as the default label when creating boxes.
+            enable_keyboard_shortcuts: If True, the component will respond to keyboard events.
         """
 
         valid_types = ["numpy", "pil", "filepath"]
@@ -158,6 +160,7 @@ class image_annotator(Component):
         self.show_remove_button = show_remove_button
         self.handles_cursor = handles_cursor
         self.use_default_label = use_default_label
+        self.enable_keyboard_shortcuts = enable_keyboard_shortcuts
 
         self.boxes_alpha = boxes_alpha
         self.box_min_size = box_min_size

src/demo/app.py

@@ -94,5 +94,16 @@ with gr.Blocks() as demo:
 
         gr.Examples(examples_crop, annotator_crop)
 
+    with gr.Accordion("Keyboard Shortcuts"):
+        gr.Markdown("""
+        - ``C``: Create mode
+        - ``D``: Drag mode
+        - ``E``: Edit selected box (same as double-click a box)
+        - ``Delete``: Remove selected box
+        - ``Space``: Reset view (zoom/pan)
+        - ``Enter``: Confirm modal dialog
+        - ``Escape``: Cancel/close modal dialog
+        """)
+
 if __name__ == "__main__":
     demo.launch()

src/demo/space.py

@@ -3,7 +3,7 @@ import gradio as gr
 from app import demo as app
 import os
 
-_docs = {'image_annotator': {'description': 'Creates a component to annotate images with bounding boxes. The bounding boxes can be created and edited by the user or be passed by code.\nIt is also possible to predefine a set of valid classes and colors.', 'members': {'__init__': {'value': {'type': 'dict | None', 'default': 'None', 'description': "A dict or None. The dictionary must contain a key 'image' with either an URL to an image, a numpy image or a PIL image. Optionally it may contain a key 'boxes' with a list of boxes. Each box must be a dict wit the keys: 'xmin', 'ymin', 'xmax' and 'ymax' with the absolute image coordinates of the box. Optionally can also include the keys 'label' and 'color' describing the label and color of the box. Color must be a tuple of RGB values (e.g. `(255,255,255)`). Optionally can also include the keys 'orientation' with a integer between 0 and 3, describing the number of times the image is rotated by 90 degrees in frontend, the rotation is clockwise."}, 'boxes_alpha': {'type': 'float | None', 'default': 'None', 'description': 'Opacity of the bounding boxes 0 and 1.'}, 'label_list': {'type': 'list[str] | None', 'default': 'None', 'description': 'List of valid labels.'}, 'label_colors': {'type': 'list[str] | None', 'default': 'None', 'description': 'Optional list of colors for each label when `label_list` is used. Colors must be a tuple of RGB values (e.g. `(255,255,255)`).'}, 'box_min_size': {'type': 'int | None', 'default': 'None', 'description': 'Minimum valid bounding box size.'}, 'handle_size': {'type': 'int | None', 'default': 'None', 'description': 'Size of the bounding box resize handles.'}, 'box_thickness': {'type': 'int | None', 'default': 'None', 'description': 'Thickness of the bounding box outline.'}, 'box_selected_thickness': {'type': 'int | None', 'default': 'None', 'description': 'Thickness of the bounding box outline when it is selected.'}, 'disable_edit_boxes': {'type': 'bool | None', 'default': 'None', 'description': 'Disables the ability to set and edit the label and color of the boxes.'}, 'single_box': {'type': 'bool', 'default': 'False', 'description': 'If True, at most one box can be drawn.'}, 'height': {'type': 'int | str | None', 'default': 'None', 'description': 'The height of the displayed image, specified in pixels if a number is passed, or in CSS units if a string is passed.'}, 'width': {'type': 'int | str | None', 'default': 'None', 'description': 'The width of the displayed image, specified in pixels if a number is passed, or in CSS units if a string is passed.'}, 'image_mode': {'type': '"1"\n    | "L"\n    | "P"\n    | "RGB"\n    | "RGBA"\n    | "CMYK"\n    | "YCbCr"\n    | "LAB"\n    | "HSV"\n    | "I"\n    | "F"', 'default': '"RGB"', 'description': '"RGB" if color, or "L" if black and white. See https://pillow.readthedocs.io/en/stable/handbook/concepts.html for other supported image modes and their meaning.'}, 'sources': {'type': 'list["upload" | "webcam" | "clipboard"] | None', 'default': '["upload", "webcam", "clipboard"]', 'description': 'List of sources for the image. "upload" creates a box where user can drop an image file, "webcam" allows user to take snapshot from their webcam, "clipboard" allows users to paste an image from the clipboard. If None, defaults to ["upload", "webcam", "clipboard"].'}, 'image_type': {'type': '"numpy" | "pil" | "filepath"', 'default': '"numpy"', 'description': 'The format the image is converted before being passed into the prediction function. "numpy" converts the image to a numpy array with shape (height, width, 3) and values from 0 to 255, "pil" converts the image to a PIL image object, "filepath" passes a str path to a temporary file containing the image. If the image is SVG, the `type` is ignored and the filepath of the SVG is returned.'}, 'label': {'type': 'str | None', 'default': 'None', 'description': 'The label for this component. Appears above the component and is also used as the header if there are a table of examples for this component. If None and used in a `gr.Interface`, the label will be the name of the parameter this component is assigned to.'}, 'container': {'type': 'bool', 'default': 'True', 'description': 'If True, will place the component in a container - providing some extra padding around the border.'}, 'scale': {'type': 'int | None', 'default': 'None', 'description': 'relative size compared to adjacent Components. For example if Components A and B are in a Row, and A has scale=2, and B has scale=1, A will be twice as wide as B. Should be an integer. scale applies in Rows, and to top-level Components in Blocks where fill_height=True.'}, 'min_width': {'type': 'int', 'default': '160', 'description': 'minimum pixel width, will wrap if not sufficient screen space to satisfy this value. If a certain scale value results in this Component being narrower than min_width, the min_width parameter will be respected first.'}, 'interactive': {'type': 'bool | None', 'default': 'True', 'description': 'if True, will allow users to upload and annotate an image; if False, can only be used to display annotated images.'}, 'visible': {'type': 'bool', 'default': 'True', 'description': 'If False, component will be hidden.'}, 'elem_id': {'type': 'str | None', 'default': 'None', 'description': 'An optional string that is assigned as the id of this component in the HTML DOM. Can be used for targeting CSS styles.'}, 'elem_classes': {'type': 'list[str] | str | None', 'default': 'None', 'description': 'An optional list of strings that are assigned as the classes of this component in the HTML DOM. Can be used for targeting CSS styles.'}, 'render': {'type': 'bool', 'default': 'True', 'description': 'If False, component will not render be rendered in the Blocks context. Should be used if the intention is to assign event listeners now but render the component later.'}, 'show_label': {'type': 'bool | None', 'default': 'None', 'description': 'if True, will display label.'}, 'show_download_button': {'type': 'bool', 'default': 'True', 'description': 'If True, will show a button to download the image.'}, 'show_share_button': {'type': 'bool | None', 'default': 'None', 'description': 'If True, will show a share icon in the corner of the component that allows user to share outputs to Hugging Face Spaces Discussions. If False, icon does not appear. If set to None (default behavior), then the icon appears if this Gradio app is launched on Spaces, but not otherwise.'}, 'show_clear_button': {'type': 'bool | None', 'default': 'True', 'description': 'If True, will show a button to clear the current image.'}, 'show_remove_button': {'type': 'bool | None', 'default': 'None', 'description': 'If True, will show a button to remove the selected bounding box.'}, 'handles_cursor': {'type': 'bool | None', 'default': 'True', 'description': 'If True, the cursor will change when hovering over box handles in drag mode. Can be CPU-intensive.'}, 'use_default_label': {'type': 'bool | None', 'default': 'False', 'description': 'If True, the first item in label_list will be used as the default label when creating boxes.'}}, 'postprocess': {'value': {'type': 'AnnotatedImageValue | None', 'description': 'A dict with an image and an optional list of boxes or None.'}}, 'preprocess': {'return': {'type': 'AnnotatedImageValue | None', 'description': 'A dict with the image and boxes or None.'}, 'value': None}}, 'events': {'clear': {'type': None, 'default': None, 'description': 'This listener is triggered when the user clears the image_annotator using the clear button for the component.'}, 'change': {'type': None, 'default': None, 'description': 'Triggered when the value of the image_annotator changes either because of user input (e.g. a user types in a textbox) OR because of a function update (e.g. an image receives a value from the output of an event trigger). See `.input()` for a listener that is only triggered by user input.'}, 'upload': {'type': None, 'default': None, 'description': 'This listener is triggered when the user uploads a file into the image_annotator.'}}}, '__meta__': {'additional_interfaces': {'AnnotatedImageValue': {'source': 'class AnnotatedImageValue(TypedDict):\n    image: Optional[np.ndarray | PIL.Image.Image | str]\n    boxes: Optional[List[dict]]\n    orientation: Optional[int]'}}, 'user_fn_refs': {'image_annotator': ['AnnotatedImageValue']}}}
+_docs = {'image_annotator': {'description': 'Creates a component to annotate images with bounding boxes. The bounding boxes can be created and edited by the user or be passed by code.\nIt is also possible to predefine a set of valid classes and colors.', 'members': {'__init__': {'value': {'type': 'dict | None', 'default': 'None', 'description': "A dict or None. The dictionary must contain a key 'image' with either an URL to an image, a numpy image or a PIL image. Optionally it may contain a key 'boxes' with a list of boxes. Each box must be a dict wit the keys: 'xmin', 'ymin', 'xmax' and 'ymax' with the absolute image coordinates of the box. Optionally can also include the keys 'label' and 'color' describing the label and color of the box. Color must be a tuple of RGB values (e.g. `(255,255,255)`). Optionally can also include the keys 'orientation' with a integer between 0 and 3, describing the number of times the image is rotated by 90 degrees in frontend, the rotation is clockwise."}, 'boxes_alpha': {'type': 'float | None', 'default': 'None', 'description': 'Opacity of the bounding boxes 0 and 1.'}, 'label_list': {'type': 'list[str] | None', 'default': 'None', 'description': 'List of valid labels.'}, 'label_colors': {'type': 'list[str] | None', 'default': 'None', 'description': 'Optional list of colors for each label when `label_list` is used. Colors must be a tuple of RGB values (e.g. `(255,255,255)`).'}, 'box_min_size': {'type': 'int | None', 'default': 'None', 'description': 'Minimum valid bounding box size.'}, 'handle_size': {'type': 'int | None', 'default': 'None', 'description': 'Size of the bounding box resize handles.'}, 'box_thickness': {'type': 'int | None', 'default': 'None', 'description': 'Thickness of the bounding box outline.'}, 'box_selected_thickness': {'type': 'int | None', 'default': 'None', 'description': 'Thickness of the bounding box outline when it is selected.'}, 'disable_edit_boxes': {'type': 'bool | None', 'default': 'None', 'description': 'Disables the ability to set and edit the label and color of the boxes.'}, 'single_box': {'type': 'bool', 'default': 'False', 'description': 'If True, at most one box can be drawn.'}, 'height': {'type': 'int | str | None', 'default': 'None', 'description': 'The height of the displayed image, specified in pixels if a number is passed, or in CSS units if a string is passed.'}, 'width': {'type': 'int | str | None', 'default': 'None', 'description': 'The width of the displayed image, specified in pixels if a number is passed, or in CSS units if a string is passed.'}, 'image_mode': {'type': '"1"\n    | "L"\n    | "P"\n    | "RGB"\n    | "RGBA"\n    | "CMYK"\n    | "YCbCr"\n    | "LAB"\n    | "HSV"\n    | "I"\n    | "F"', 'default': '"RGB"', 'description': '"RGB" if color, or "L" if black and white. See https://pillow.readthedocs.io/en/stable/handbook/concepts.html for other supported image modes and their meaning.'}, 'sources': {'type': 'list["upload" | "webcam" | "clipboard"] | None', 'default': '["upload", "webcam", "clipboard"]', 'description': 'List of sources for the image. "upload" creates a box where user can drop an image file, "webcam" allows user to take snapshot from their webcam, "clipboard" allows users to paste an image from the clipboard. If None, defaults to ["upload", "webcam", "clipboard"].'}, 'image_type': {'type': '"numpy" | "pil" | "filepath"', 'default': '"numpy"', 'description': 'The format the image is converted before being passed into the prediction function. "numpy" converts the image to a numpy array with shape (height, width, 3) and values from 0 to 255, "pil" converts the image to a PIL image object, "filepath" passes a str path to a temporary file containing the image. If the image is SVG, the `type` is ignored and the filepath of the SVG is returned.'}, 'label': {'type': 'str | None', 'default': 'None', 'description': 'The label for this component. Appears above the component and is also used as the header if there are a table of examples for this component. If None and used in a `gr.Interface`, the label will be the name of the parameter this component is assigned to.'}, 'container': {'type': 'bool', 'default': 'True', 'description': 'If True, will place the component in a container - providing some extra padding around the border.'}, 'scale': {'type': 'int | None', 'default': 'None', 'description': 'relative size compared to adjacent Components. For example if Components A and B are in a Row, and A has scale=2, and B has scale=1, A will be twice as wide as B. Should be an integer. scale applies in Rows, and to top-level Components in Blocks where fill_height=True.'}, 'min_width': {'type': 'int', 'default': '160', 'description': 'minimum pixel width, will wrap if not sufficient screen space to satisfy this value. If a certain scale value results in this Component being narrower than min_width, the min_width parameter will be respected first.'}, 'interactive': {'type': 'bool | None', 'default': 'True', 'description': 'if True, will allow users to upload and annotate an image; if False, can only be used to display annotated images.'}, 'visible': {'type': 'bool', 'default': 'True', 'description': 'If False, component will be hidden.'}, 'elem_id': {'type': 'str | None', 'default': 'None', 'description': 'An optional string that is assigned as the id of this component in the HTML DOM. Can be used for targeting CSS styles.'}, 'elem_classes': {'type': 'list[str] | str | None', 'default': 'None', 'description': 'An optional list of strings that are assigned as the classes of this component in the HTML DOM. Can be used for targeting CSS styles.'}, 'render': {'type': 'bool', 'default': 'True', 'description': 'If False, component will not render be rendered in the Blocks context. Should be used if the intention is to assign event listeners now but render the component later.'}, 'show_label': {'type': 'bool | None', 'default': 'None', 'description': 'if True, will display label.'}, 'show_download_button': {'type': 'bool', 'default': 'True', 'description': 'If True, will show a button to download the image.'}, 'show_share_button': {'type': 'bool | None', 'default': 'None', 'description': 'If True, will show a share icon in the corner of the component that allows user to share outputs to Hugging Face Spaces Discussions. If False, icon does not appear. If set to None (default behavior), then the icon appears if this Gradio app is launched on Spaces, but not otherwise.'}, 'show_clear_button': {'type': 'bool | None', 'default': 'True', 'description': 'If True, will show a button to clear the current image.'}, 'show_remove_button': {'type': 'bool | None', 'default': 'None', 'description': 'If True, will show a button to remove the selected bounding box.'}, 'handles_cursor': {'type': 'bool | None', 'default': 'True', 'description': 'If True, the cursor will change when hovering over box handles in drag mode. Can be CPU-intensive.'}, 'use_default_label': {'type': 'bool | None', 'default': 'False', 'description': 'If True, the first item in label_list will be used as the default label when creating boxes.'}, 'enable_keyboard_shortcuts': {'type': 'bool', 'default': 'True', 'description': 'If True, the component will respond to keyboard events.'}}, 'postprocess': {'value': {'type': 'AnnotatedImageValue | None', 'description': 'A dict with an image and an optional list of boxes or None.'}}, 'preprocess': {'return': {'type': 'AnnotatedImageValue | None', 'description': 'A dict with the image and boxes or None.'}, 'value': None}}, 'events': {'clear': {'type': None, 'default': None, 'description': 'This listener is triggered when the user clears the image_annotator using the clear button for the component.'}, 'change': {'type': None, 'default': None, 'description': 'Triggered when the value of the image_annotator changes either because of user input (e.g. a user types in a textbox) OR because of a function update (e.g. an image receives a value from the output of an event trigger). See `.input()` for a listener that is only triggered by user input.'}, 'upload': {'type': None, 'default': None, 'description': 'This listener is triggered when the user uploads a file into the image_annotator.'}}}, '__meta__': {'additional_interfaces': {'AnnotatedImageValue': {'source': 'class AnnotatedImageValue(TypedDict):\n    image: Optional[np.ndarray | PIL.Image.Image | str]\n    boxes: Optional[List[dict]]\n    orientation: Optional[int]'}}, 'user_fn_refs': {'image_annotator': ['AnnotatedImageValue']}}}
 
 abs_path = os.path.join(os.path.dirname(__file__), "css.css")
 
@@ -133,6 +133,17 @@ with gr.Blocks() as demo:
         button_crop.click(crop, annotator_crop, image_crop)
 
         gr.Examples(examples_crop, annotator_crop)
+    
+    with gr.Accordion("Keyboard Shortcuts"):
+        gr.Markdown(\"\"\"
+        - ``C``: Create mode
+        - ``D``: Drag mode
+        - ``E``: Edit selected box (same as double-click a box)
+        - ``Delete``: Remove selected box
+        - ``Space``: Reset view (zoom/pan)
+        - ``Enter``: Confirm modal dialog
+        - ``Escape``: Cancel/close modal dialog
+        \"\"\")
 
 if __name__ == "__main__":
     demo.launch()

src/frontend/Index.svelte

@@ -50,6 +50,7 @@
 	export let show_remove_button: boolean;
 	export let handles_cursor: boolean;
 	export let use_default_label: boolean;
+	export let enable_keyboard_shortcuts: boolean;
 
 	export let gradio: Gradio<{
 		change: never;
@@ -129,6 +130,7 @@
 		showRemoveButton={show_remove_button}
 		handlesCursor={handles_cursor}
 		useDefaultLabel={use_default_label}
+		enableKeyboardShortcuts={enable_keyboard_shortcuts}
 	>
 		{#if active_source === "upload"}
 			<UploadText i18n={gradio.i18n} type="image" />

src/frontend/shared/Canvas.svelte

@@ -1,5 +1,5 @@
 <script lang="ts">
-    import { onMount, onDestroy, createEventDispatcher } from "svelte";
+    import { onMount, createEventDispatcher } from "svelte";
 	import { BoundingBox, Hand, Trash, Label } from "./icons/index";
 	import ModalBox from "./ModalBox.svelte";
 	import Box from "./Box";
@@ -27,12 +27,14 @@
 	export let showRemoveButton: boolean = null;
 	export let handlesCursor: boolean = true;
 	export let useDefaultLabel: boolean = false;
+	export let enableKeyboardShortcuts: boolean = true;
 
 	if (showRemoveButton === null) {
 		showRemoveButton = (disableEditBoxes);
 	}
 
     let canvas: HTMLCanvasElement;
+	let annotatorContainerDiv: HTMLDivElement;
 	let ctx: CanvasRenderingContext2D;
     let image = null;
 	let selectedBox = -1;
@@ -309,16 +311,44 @@
 		}
 	}
 
+	function resetView() {
+		// Calculate minimum scale to fit image
+		const scaleX = canvas.width / imageWidth;
+		const scaleY = canvas.height / imageHeight;
+		const minScale = Math.min(scaleX, scaleY);
+				
+		// Set scale and center
+		canvasWindow.scale = minScale;
+		canvasWindow.offsetX = (canvas.width - imageWidth * minScale) / 2;
+		canvasWindow.offsetY = (canvas.height - imageHeight * minScale) / 2;
+		
+		draw();
+	}
+
 	function handleKeyPress(event: KeyboardEvent) {
-		if (!interactive) {
+		if (!enableKeyboardShortcuts || event.target !== annotatorContainerDiv || !interactive) {
 			return;
 		}
+		
+		const key = event.key.toLowerCase();
+		const blockedKeys = new Set(['delete', 'c', 'd', 'e', ' ']);
 
-		switch (event.key) {
-			case "Delete":
-				onDeleteBox();
-				break;
+		if (blockedKeys.has(key)) {
+			event.preventDefault();
+			event.stopPropagation();
 		}
+		
+		switch (key) {
+			case 'delete': onDeleteBox(); break;
+			case 'c': setCreateMode(); break;
+			case 'd': setDragMode(); break;
+			case 'e': onEditBox(); break;
+			case ' ': resetView(); break;
+		}
+	}
+
+	function focusAnnotator() {
+		setTimeout(() => {annotatorContainerDiv?.focus();}, 0);
 	}
 
 	function handleMouseWheel(event: WheelEvent) {
@@ -439,6 +469,7 @@
 
 	function onModalEditChange(event) {
 		editModalVisible = false;
+		focusAnnotator();
 		const { detail } = event;
 		let label = detail.label;
 		let color = detail.color;
@@ -458,6 +489,7 @@
 
 	function onModalNewChange(event) {
 		newModalVisible = false;
+		focusAnnotator();
 		const { detail } = event;
 		let label = detail.label;
 		let color = detail.color;
@@ -481,6 +513,7 @@
 
 	function onDefaultLabelEditChange(event) {
 		editDefaultLabelVisible = false;
+		focusAnnotator();
 		const { detail } = event;
 		let label = detail.label;
 		let color = detail.color;
@@ -670,84 +703,84 @@
 		if (selectedBox < 0 && value !== null && value.boxes.length > 0) {
 			selectBox(0);
 		}
+		
 		setImage();
 		resize();
 		draw();
 	});
-	
-	function handleCanvasFocus() {
-		document.addEventListener("keydown", handleKeyPress);
-	}
-	
-	function handleCanvasBlur() {
-		document.removeEventListener("keydown", handleKeyPress);
-	}
-
-	onDestroy(() => {
-		document.removeEventListener("keydown", handleKeyPress);
-  	});
 
 </script>
 
+<!-- svelte-ignore a11y-no-noninteractive-tabindex -->
+<!-- svelte-ignore a11y-no-static-element-interactions -->
 <div
-	class="canvas-container"
-	tabindex="-1"
-	on:focusin={handleCanvasFocus}
-	on:focusout={handleCanvasBlur}
+	class="annotator-container"
+	tabindex="0"
+	bind:this={annotatorContainerDiv}
+	on:keydown={handleKeyPress}
+	on:click={() => annotatorContainerDiv.focus()}
 >
-	<canvas
-		bind:this={canvas}
-		on:pointerdown={handlePointerDown}
-		on:pointerup={handlePointerUp}
-		on:pointermove={handlePointerMove}
-		on:pointercancel={handlePointerCancel}
-		on:dblclick={handleDoubleClick}
-		on:wheel={handleMouseWheel}
-		style="height: {height}; width: {width};"
-		class="canvas-annotator"
-	></canvas>
-</div>
-
-{#if interactive}
-	<span class="canvas-control">
-		<button
-			class="icon"
-			class:selected={mode === Mode.creation}
-			aria-label="Create box"
-			on:click={() => setCreateMode()}><BoundingBox/></button
-		>
-		<button
-			class="icon"
-			class:selected={mode === Mode.drag}
-			aria-label="Edit boxes"
-			on:click={() => setDragMode()}><Hand/></button
-		>
-		{#if showRemoveButton}
+	<div class="canvas-container">
+		<canvas
+			bind:this={canvas}
+			on:pointerdown={handlePointerDown}
+			on:pointerup={handlePointerUp}
+			on:pointermove={handlePointerMove}
+			on:pointercancel={handlePointerCancel}
+			on:dblclick={handleDoubleClick}
+			on:wheel={handleMouseWheel}
+			style="height: {height}; width: {width};"
+			class="canvas-annotator"
+		></canvas>
+	</div>
+
+	{#if interactive}
+		<span class="canvas-control">
 			<button
 				class="icon"
-				aria-label="Remove boxes"
-				on:click={() => onDeleteBox()}><Trash/></button
+				class:selected={mode === Mode.creation}
+				aria-label="Create box"
+				title="Create box (C)"
+				on:click={() => setCreateMode()}><BoundingBox/></button
 			>
-		{/if}
-		{#if !disableEditBoxes && labelDetailLock}
 			<button
 				class="icon"
-				aria-label="Edit label"
-				on:click={() => editDefaultLabelVisible = true}><Label/></button
+				class:selected={mode === Mode.drag}
+				aria-label="Drag boxes"
+				title="Drag boxes (D)"
+				on:click={() => setDragMode()}><Hand/></button
 			>
-		{/if}
-		<button
-			class="icon"
-			aria-label="Rotate counterclockwise"
-			on:click={() => onRotateImage(-1)}><Undo/></button
-		>
-		<button
-			class="icon"
-			aria-label="Rotate clockwise"
-			on:click={() => onRotateImage(1)}><Redo/></button
-		>
-	</span>
-{/if}
+			{#if showRemoveButton}
+				<button
+					class="icon"
+					aria-label="Remove box"
+					title="Remove box (Del)"
+					on:click={() => onDeleteBox()}><Trash/></button
+				>
+			{/if}
+			{#if !disableEditBoxes && labelDetailLock}
+				<button
+					class="icon"
+					aria-label="Edit label"
+					title="Edit label"
+					on:click={() => editDefaultLabelVisible = true}><Label/></button
+				>
+			{/if}
+			<button
+				class="icon"
+				aria-label="Rotate counterclockwise"
+				title="Rotate counterclockwise"
+				on:click={() => onRotateImage(-1)}><Undo/></button
+			>
+			<button
+				class="icon"
+				aria-label="Rotate clockwise"
+				title="Rotate clockwise"
+				on:click={() => onRotateImage(1)}><Redo/></button
+			>
+		</span>
+	{/if}
+</div>
 
 {#if editModalVisible}
 	<ModalBox

src/frontend/shared/ImageAnnotator.svelte

@@ -42,6 +42,7 @@
 	export let cli_upload: Client["upload"];
 	export let stream_handler: Client["stream_factory"];
 	export let useDefaultLabel: boolean;
+	export let enableKeyboardShortcuts: boolean;
 
 	let upload: Upload;
 	let uploading = false;
@@ -189,6 +190,7 @@
 					{handlesCursor}
 					{boxSelectedThickness}
 					{useDefaultLabel}
+					{enableKeyboardShortcuts}
 					src={value.image.url}
 				/>
 			</div>

src/frontend/shared/ImageCanvas.svelte

@@ -26,6 +26,7 @@
 	export let showRemoveButton: boolean;
 	export let handlesCursor: boolean;
 	export let useDefaultLabel: boolean;
+	export let enableKeyboardShortcuts: boolean;
 
 	let resolved_src: typeof src;
 
@@ -74,5 +75,6 @@
 	{showRemoveButton}
 	{handlesCursor}
 	{useDefaultLabel}
+	{enableKeyboardShortcuts}
 	imageUrl={resolved_src}
 />

src/frontend/shared/ModalBox.svelte

@@ -3,7 +3,7 @@
     import { BaseButton } from "@gradio/button";
     import { BaseDropdown } from "./patched_dropdown/Index.svelte";
 	import { createEventDispatcher } from "svelte";
-    import { onMount, onDestroy } from "svelte";
+    import { onMount } from "svelte";
     import { Lock, Unlock } from "./icons/index";
 
     export let label = "";
@@ -59,10 +59,13 @@
     }
 
     function handleKeyPress(event: KeyboardEvent) {
-		switch (event.key) {
-			case "Enter":
+		switch (event.key.toLowerCase()) {
+			case "enter":
                 dispatchChange(1);
 				break;
+            case "escape":
+                dispatchChange(0);
+				break;
 		}
 	}
 
@@ -70,11 +73,11 @@
 		document.addEventListener("keydown", handleKeyPress);
         currentLabel = label;
         currentColor = color;
+
+        return () => {
+            document.removeEventListener("keydown", handleKeyPress);
+        };
 	});
-    
-	onDestroy(() => {
-        document.removeEventListener("keydown", handleKeyPress);
-  	});
 
 </script>
 

src/pyproject.toml

@@ -8,7 +8,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "gradio_image_annotation"
-version = "0.3.1"
+version = "0.4.0"
 description = "A Gradio component that can be used to annotate images with bounding boxes."
 readme = "README.md"
 license = "MIT"