File size: 5,312 Bytes
5738e29 ae9e8d1 5738e29 ae9e8d1 5738e29 ae9e8d1 5738e29 1811a2f 5738e29 |
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 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 |
import os
import socket
import time
import gradio as gr
import numpy as np
from PIL import Image, ImageDraw
import base64
import requests
import json
# API for inferences
DL4EO_API_URL = "https://dl4eo--object-predict-raster.modal.run"
# Auth Token to access API
DL4EO_API_KEY = os.environ['DL4EO_API_KEY']
# width of the boxes on image
LINE_WIDTH = 2
# Check Gradio version
print(f"Gradio version: {gr.__version__}")
# Define the inference function
def predict_image(img, threshold):
if isinstance(img, Image.Image):
img = np.array(img)
if not isinstance(img, np.ndarray) or len(img.shape) != 3 or img.shape[2] != 3:
raise BaseException("predit_image(): input 'img' shoud be single RGB image in PIL or Numpy array format.")
# Encode the image data as base64
image_base64 = base64.b64encode(np.ascontiguousarray(img)).decode()
# Create a dictionary representing the JSON payload
payload = {
'image': image_base64,
'shape': img.shape,
'threshold': threshold,
}
headers = {
'Authorization': 'Bearer ' + DL4EO_API_KEY,
'Content-Type': 'application/json' # Adjust the content type as needed
}
# Send the POST request to the API endpoint with the image file as binary payload
response = requests.post(DL4EO_API_URL, json=payload, headers=headers)
# Check the response status
if response.status_code != 200:
raise Exception(
f"Received status code={response.status_code} in inference API"
)
json_data = json.loads(response.content)
image_data = json_data['image']
shape = json_data['shape']
infos = json_data['infos']
duration = json_data['duration']
img_data_in = base64.b64decode(json_data['image'])
np_img = np.frombuffer(img_data_in, dtype=np.uint8).reshape(shape)
pil_img = Image.fromarray(np_img)
return pil_img, shape, infos, duration
# Define example images and their true labels for users to choose from
example_data = [
["./demo/demo.jpg", 0.8],
["./demo/dota_demo.jpg", 0.8],
["./demo/Satellite_Image_Marina_New_Zealand.jpg", 0.8],
["./demo/Pleiades_HD15_Miami_Marina.jpg", 0.8],
["./demo/SPOT_Storage.jpg", 0.8],
["./demo/airport01.jpg", 0.8],
["./demo/Pleiades_Neo_Tucson_USA.jpg", 0.8],
# Add more example images and labels as needed
]
# Define CSS for some elements
css = """
.image-preview {
height: 820px !important;
width: 800px !important;
}
"""
TITLE = "Oriented bounding boxes detection on Optical Satellite images"
# Define the Gradio Interface
demo = gr.Blocks(title=TITLE, css=css).queue()
with demo:
gr.Markdown(f"<h1><center>{TITLE}<center><h1>")
with gr.Row():
with gr.Column(scale=0):
input_image = gr.Image(type="pil", interactive=True)
run_button = gr.Button(value="Run")
with gr.Accordion("Advanced options", open=True):
threshold = gr.Slider(label="Confidence threshold", minimum=0.0, maximum=1.0, value=0.25, step=0.01)
dimensions = gr.Textbox(label="Image size", interactive=False)
detections = gr.Textbox(label="Predicted objects", interactive=False)
stopwatch = gr.Number(label="Execution time (sec.)", interactive=False, precision=3)
with gr.Column(scale=2):
output_image = gr.Image(type="pil", elem_classes='image-preview', interactive=False)
run_button.click(fn=predict_image, inputs=[input_image, threshold], outputs=[output_image, dimensions, detections, stopwatch])
gr.Examples(
examples=example_data,
inputs = [input_image, threshold],
outputs = [output_image, dimensions, detections, stopwatch],
fn=predict_image,
cache_examples=False,
label='Try these images!'
)
gr.Markdown("""
<p>This demo is provided by <a href='https://www.linkedin.com/in/faudi/'>Jeff Faudi</a> and <a href='https://www.dl4eo.com/'>DL4EO</a>.
This model is based on the <a href='https://github.com/open-mmlab/mmrotate'>MMRotate framework</a> which provides oriented bounding boxes.
We believe that oriented bouding boxes are better suited for detection in satellite images. This model has been trained on the
<a href='https://captain-whu.github.io/DOTA/dataset.html'>DOTA dataset</a> which contains 15 classes: plane, ship, storage tank,
baseball diamond, tennis court, basketball court, ground track field, harbor, bridge, large vehicle, small vehicle, helicopter,
roundabout, soccer ball field and swimming pool. </p><p>The associated licenses are
<a href='https://about.google/brand-resource-center/products-and-services/geo-guidelines/#google-earth-web-and-apps'>GoogleEarth fair use</a>
and <a href='https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en'>CC-BY-SA-NC</a>. This demonstration CANNOT be used for commercial puposes.
Please contact <a href='mailto:[email protected]'>me</a> for more information on how you could get access to a commercial grade model or API. </p>")
""")
demo.launch(
inline=False,
show_api=False,
debug=False
)
|