Inital commit

.gitignore

@@ -0,0 +1,2 @@
+MobileNetSSD_deploy.caffemodel
+MobileNetSSD_deploy.prototxt

app.py

@@ -0,0 +1,68 @@
+import cv2
+import numpy as np
+import gradio as gr
+
+net = cv2.dnn.readNetFromCaffe(
+    "MobileNetSSD_deploy.prototxt", "MobileNetSSD_deploy.caffemodel"
+)
+
+class_names = [
+    "background",
+    "aeroplane",
+    "bicycle",
+    "bird",
+    "boat",
+    "bottle",
+    "bus",
+    "car",
+    "cat",
+    "chair",
+    "cow",
+    "diningtable",
+    "dog",
+    "horse",
+    "motorbike",
+    "person",
+    "pottedplant",
+    "sheep",
+    "sofa",
+    "train",
+    "tvmonitor",
+]
+
+
+def detect_objects(image):
+    frame = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+    blob = cv2.dnn.blobFromImage(
+        frame, 0.007843, (300, 300), (127.5, 127.5, 127.5), swapRB=False, crop=False
+    )
+    net.setInput(blob)
+    detections = net.forward()
+
+    for i in range(detections.shape[2]):
+        confidence = detections[0, 0, i, 2]
+        if confidence > 0.2:
+            idx = int(detections[0, 0, i, 1])
+            box = detections[0, 0, i, 3:7] * np.array(
+                [frame.shape[1], frame.shape[0], frame.shape[1], frame.shape[0]]
+            )
+            (startX, startY, endX, endY) = box.astype("int")
+
+            label = f"{class_names[idx]}: {confidence:.2f}"
+            cv2.rectangle(frame, (startX, startY), (endX, endY), (0, 255, 0), 2)
+            y = startY - 15 if startY - 15 > 15 else startY + 15
+            cv2.putText(
+                frame,
+                label,
+                (startX, y),
+                cv2.FONT_HERSHEY_SIMPLEX,
+                0.5,
+                (255, 255, 255),
+                2,
+            )
+
+    return cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+
+
+iface = gr.Interface(fn=detect_objects, inputs="image", outputs="image", live=True)
+iface.launch()

requirements.txt

@@ -0,0 +1,53 @@
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.6.2.post1
+certifi==2024.8.30
+charset-normalizer==3.4.0
+click==8.1.7
+fastapi==0.115.3
+ffmpy==0.4.0
+filelock==3.16.1
+fsspec==2024.10.0
+gradio==5.4.0
+gradio_client==1.4.2
+h11==0.14.0
+httpcore==1.0.6
+httpx==0.27.2
+huggingface-hub==0.26.1
+idna==3.10
+Jinja2==3.1.4
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+numpy==2.1.2
+opencv-python==4.10.0.84
+opencv-python-headless==4.10.0.84
+orjson==3.10.10
+packaging==24.1
+pandas==2.2.3
+pillow==11.0.0
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydub==0.25.1
+Pygments==2.18.0
+python-dateutil==2.9.0.post0
+python-multipart==0.0.12
+pytz==2024.2
+PyYAML==6.0.2
+requests==2.32.3
+rich==13.9.3
+ruff==0.7.1
+safehttpx==0.1.1
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.41.2
+tomlkit==0.12.0
+tqdm==4.66.5
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uvicorn==0.32.0
+websockets==12.0