feat($app): initial push

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+sample.jpeg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,6 +1,6 @@
 ---
 title: Crowd Counter
-emoji: 🐢
+emoji: 👨‍👩‍👦‍👦 ∑
 colorFrom: gray
 colorTo: red
 sdk: gradio

app.py

@@ -0,0 +1,70 @@
+import gradio as gr
+import cv2
+import numpy as np
+import torch
+import kornia as K
+from kornia.core import Tensor
+from kornia.contrib import FaceDetector, FaceDetectorResult, FaceKeypoint
+
+
+def draw_keypoint(img: np.ndarray, det: FaceDetectorResult, kpt_type: FaceKeypoint) -> np.ndarray:
+    kpt = det.get_keypoint(kpt_type).int().tolist()
+    return cv2.circle(img, kpt, 2, (255, 0, 0), 2)
+
+
+def detect(img_raw):
+
+    # preprocess
+    if img_raw is not None and len(img_raw.shape) == 3:
+        img = K.image_to_tensor(img_raw, keepdim=False)
+        img = K.color.bgr_to_rgb(img.float())
+
+
+        # create the detector and find the faces !
+        face_detection = FaceDetector()
+
+        with torch.no_grad():
+            dets = face_detection(img)
+        dets = [FaceDetectorResult(o) for o in dets[0]]
+
+        img_vis = img_raw.copy()
+
+        vis_threshold = 0.8
+
+        for b in dets:
+            if b.score < vis_threshold:
+                continue
+
+            # Draw face bounding box
+            img_vis = cv2.rectangle(img_vis, b.top_left.int().tolist(), b.bottom_right.int().tolist(), (0, 255, 0), 4)
+            # Draw Keypoints
+            img_vis = draw_keypoint(img_vis, b, FaceKeypoint.EYE_LEFT)
+            img_vis = draw_keypoint(img_vis, b, FaceKeypoint.EYE_RIGHT)
+            img_vis = draw_keypoint(img_vis, b, FaceKeypoint.NOSE)
+            img_vis = draw_keypoint(img_vis, b, FaceKeypoint.MOUTH_LEFT)
+            img_vis = draw_keypoint(img_vis, b, FaceKeypoint.MOUTH_RIGHT)
+
+        return img_vis, len(dets)
+
+
+title = "Crowd Counter"
+description = "<p style='text-align: center'>This is a Gradio demo for crowd counting using Kornia's Face Detection model.</p><p style='text-align: center'>To use it, simply upload your image, or click one of the examples to load them</p>"
+article = "<p style='text-align: center'><a href='https://kornia.readthedocs.io/en/latest/' target='_blank'>Kornia Docs</a> | <a href='https://github.com/kornia/kornia' target='_blank'>Kornia Github Repo</a> | <a 
+href='https://kornia.readthedocs.io/en/latest/applications/face_detection.html' target='_blank'>Kornia Face Detection Tutorial</a></p>"
+outputs = [gr.outputs.Image(type="pil", label="Output Image"), gr.outputs.Textbox(label="Total (Head) Count")]
+
+examples = ['sample.jpeg']
+
+face = gr.Interface(
+    detect,
+    gr.inputs.Image(type="numpy"),
+    outputs=outputs,
+    examples=examples,
+    title=title,
+    description=description,
+    article=article,
+    live=True,
+    allow_flagging="never"
+)
+
+face.launch()

requirements.txt

@@ -0,0 +1,3 @@
+kornia
+opencv-python
+torch