Setup inputs and outputs

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,5 +1,5 @@
 ---
-title: Mediapipe Face Detection
+title: Mediapipe's Face Detection
 emoji: 😃
 colorFrom: indigo
 colorTo: gray

app.py

@@ -7,10 +7,51 @@ from google.protobuf.json_format import MessageToDict
 
 logger = log_utils.get_logger()
 
-import gradio as gr
+mp_face_detection = mp.solutions.face_detection
+mp_drawing = mp.solutions.drawing_utils
+
+demo = gr.Blocks()
+
+def detect_faces(image, model_selection, min_detection_confidence):
+  return {}, image
+
+with demo:
+  gr.Markdown(
+    """
+    # MediaPipe's Face Detection
+    A demo of face detection using [Google's MediaPipe](https://google.github.io/mediapipe/solutions/face_detection.html)
+    """)
+
+  with gr.Row():
+    with gr.Column():
+      
+      gr.Markdown("## Step 1: Configure the model")
+      with gr.Group():
+        model_selection = gr.Radio(label="Model selection", value=0, choices=[0, 1])
+        gr.Textbox(show_label=False, value="An integer index 0 or 1. Use 0 to select a short-range model that works best for faces within 2 meters from the camera, and 1 for a full-range model best for faces within 5 meters. For the full-range option, a sparse model is used for its improved inference speed.")
+      
+      with gr.Group():
+        min_detection_confidence = gr.Slider(label="Min detection confidence", value=0.5, minimum=0.0, maximum=1.0, step=0.01)
+        gr.Textbox(show_label=False, value="Minimum confidence value ([0.0, 1.0]) from the face detection model for the detection to be considered successful.")
+
+      gr.Markdown("## Step 2: Select an image")
+      with gr.Tabs():
+        with gr.TabItem(label="Upload an image"):
+          upload_image = gr.Image(label="Input image")
+          gr.Examples(examples=[["examples/01.jpg"]], inputs=[upload_image])
+          upload_image_btn = gr.Button(value="Detect faces")
+        with gr.TabItem(label="Take a photo"):
+          webcam_image = gr.Image(label="Input image", source="webcam")
+          webcam_image_btn = gr.Button(value="Detect faces")
+
+    with gr.Column():
+      gr.Markdown("## Step 3: View the results")
+      with gr.Group():
+        raw_results = gr.JSON(label="Raw results")
+        output_image = gr.Image(label="Output image")
 
-def greet(name):
-    return "Hello " + name + "!!"
+    model_config_inputs = [model_selection, min_detection_confidence]
+    outputs = [raw_results, output_image]
+    upload_image_btn.click(fn=detect_faces, inputs=[upload_image, *model_config_inputs], outputs=outputs)
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+demo.launch()

requirements.txt

@@ -1,3 +1,3 @@
 gradio==3.0.26
 opencv-contrib-python==4.6.0.66
-mediapy==1.0.3
+mediapipe==0.8.10.1