Initial commit

.gitattributes

@@ -33,3 +33,10 @@ 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
+demo/demo.jpg filter=lfs diff=lfs merge=lfs -text
+demo/dota_demo.jpg filter=lfs diff=lfs merge=lfs -text
+demo/Pleiades_HD15_Miami_Marina.jpg filter=lfs diff=lfs merge=lfs -text
+demo/Pleiades_Neo_Tucson_USA.jpg filter=lfs diff=lfs merge=lfs -text
+demo/SPOT_Storage.jpg filter=lfs diff=lfs merge=lfs -text
+demo/Satellite_Image_Marina_New_Zealand.jpg filter=lfs diff=lfs merge=lfs -text
+demo/airport01.jpg filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,131 @@
+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)
+    pil_img = json_data['image']
+    shape = json_data['shape']
+    infos = json_data['infos']
+    duration = json_data['duration']
+
+    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"<h3><center>{TITLE}<center><h3>")
+
+    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=True,
+        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:jeff@dl4eo.com'>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
+)