File size: 3,029 Bytes
aa8c1b9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 |
import tensorflow as tf
import cv2
import numpy as np
import gradio as gr
# Load the pre-trained MobileNet SSD model
model = tf.saved_model.load("http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v2_fpnlite_320x320/saved_model")
# Define the label map for the MobileNet SSD model
category_index = {
1: {'id': 1, 'name': 'person'},
2: {'id': 2, 'name': 'bicycle'},
3: {'id': 3, 'name': 'car'},
# Add more label mappings as needed
}
# Function to detect objects in the image
def detect_objects(image):
# Preprocess the image
input_tensor = tf.convert_to_tensor(image)
input_tensor = input_tensor[tf.newaxis,...]
# Run the model and get detections
detections = model(input_tensor)
# Process detections and draw bounding boxes
num_detections = int(detections.pop('num_detections'))
detections = {key: value[0, :num_detections].numpy() for key, value in detections.items()}
detection_classes = detections['detection_classes'].astype(np.int64)
detection_boxes = detections['detection_boxes']
detection_scores = detections['detection_scores']
# Draw boxes on the image
for i in range(num_detections):
if detection_scores[i] > 0.5: # Only consider confident detections
class_name = category_index.get(detection_classes[i], {'name': 'N/A'})['name']
box = detection_boxes[i]
height, width, _ = image.shape
ymin, xmin, ymax, xmax = box
(startX, startY, endX, endY) = (int(xmin * width), int(ymin * height), int(xmax * width), int(ymax * height))
# Draw bounding box and label
cv2.rectangle(image, (startX, startY), (endX, endY), (0, 255, 0), 2)
label = f"{class_name}: {detection_scores[i]:.2f}"
cv2.putText(image, label, (startX, startY - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
return image
# Function to handle the image from file upload or path
def gradio_interface(image):
if isinstance(image, str): # Check if it's a path string
image = cv2.imread(image)
else:
# Convert PIL image (Gradio) to OpenCV format (numpy array)
image = np.array(image)
# Convert to RGB format
image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
# Detect objects in the image
detected_image = detect_objects(image_rgb)
# Convert back to BGR for display in Gradio (OpenCV uses BGR)
detected_image_bgr = cv2.cvtColor(detected_image, cv2.COLOR_RGB2BGR)
return detected_image_bgr
# Create Gradio app with image input (supports path or upload)
iface = gr.Interface(fn=gradio_interface,
inputs=gr.inputs.Image(type="filepath"), # Use "filepath" to allow local path or upload
outputs="image",
title="Object Detection with Bounding Boxes",
description="Upload an image or provide a file path to detect objects.")
# Launch the Gradio app (for local or Hugging Face)
iface.launch()
|