[go: up one dir, main page]
Scribd
Upload
34 views3 pages

TensorFlow Object Detection Guide

The document describes using a TensorFlow Object Detection model to detect objects in an image and display the locations of detected objects on a map. It first shows installing required packages and downloading a pre-trained model. Then a Python script is shown that loads the model, detects objects in an image, and initializes a map to display the GPS coordinates of detections.

Uploaded by

Rafael Raña
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
34 views3 pages

TensorFlow Object Detection Guide

The document describes using a TensorFlow Object Detection model to detect objects in an image and display the locations of detected objects on a map. It first shows installing required packages and downloading a pre-trained model. Then a Python script is shown that loads the model, detects objects in an image, and initializes a map to display the GPS coordinates of detections.

Uploaded by

Rafael Raña
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

First, let's start with installing the required packages:

pip install tensorflow object-detection-api opencv-python-headless

Next, download the pre-trained TensorFlow Object Detection model:

MODEL_NAME = 'ssd_mobilenet_v1_coco_2017_11_17'

MODEL_FILE = MODEL_NAME + '.tar.gz'

DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'

opener = urllib.request.URLopener()

opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_NAME + '.tar.gz')

tar_file = tarfile.open(MODEL_NAME + '.tar.gz')

for file in tar_file.getmembers():

file_name = os.path.basename(file.name)

if 'frozen_inference_graph.pb' in file_name:

tar_file.extract(file, os.getcwd())

Now, let's write a Python script that uses the TensorFlow Object Detection model to detect
objects in an image and uses GPS coordinates to display the location of the detected objects on
a map.

import cv2

import numpy as np

import tensorflow as tf

from mtcnn.mtcnn import MTCNN

import folium

# Load the pre-trained TensorFlow Object Detection model

model = tf.saved_model.load('path/to/model')

# Load the MTCNN model for face detection

mtcnn = MTCNN()
# Initialize the GPS coordinates

gps_coordinates = (51.5074, -0.1278) # London

# Initialize the map

m = folium.Map(location=gps_coordinates,

Python code that uses TensorFlow Object Detection API to detect objects in an image:

import cv2

import numpy as np

import tensorflow as tf

# Load the pre-trained TensorFlow Object Detection model

model = tf.saved_model.load('path/to/model')

# Load the image

image = cv2.imread('path/to/image')

# Pre-process the image for object detection

input_tensor = tf.convert_to_tensor(image)

input_tensor = input_tensor[tf.newaxis, ...]

# Perform object detection

detections = model(input_tensor)

# Process the detections

num_detections = int(detections.pop('num_detections'))

detections = {key: value[0, :num_detections].numpy()


for key, value in detections.items()}

detections['num_detections'] = num_detections

# Draw the bounding boxes and labels on the image

for i in range(num_detections):

class_id = detections['detection_classes'][i]

score = detections['detection_scores'][i]

x1, y1, x2, y2 =

You might also like