First commit

.gitattributes

@@ -33,3 +33,9 @@ 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/two-dogs-with-a-stick.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

README.md

@@ -1,6 +1,6 @@
 ---
 title: Open Detection Optical Satellite
-emoji: 📊
+emoji: 👀
 colorFrom: indigo
 colorTo: red
 sdk: gradio

app.py

@@ -0,0 +1,152 @@
+import os
+import socket
+import gradio as gr
+import numpy as np
+from PIL import Image, ImageDraw
+from pathlib import Path
+from loguru import logger
+import cv2
+import torch
+import ultralytics
+from ultralytics import YOLO
+import time
+import base64
+import requests
+import json
+ 
+# API for inferences
+DL4EO_API_URL = "https://dl4eo--groundingdino-predict-dev.modal.run"
+#DL4EO_API_URL = "https://dl4eo--groundingdino-predict.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 modules version
+logger.info(f"Gradio version: {gr.__version__}")
+
+# Define the inference function
+def predict_image(image, threshold):
+    
+    # Resize the image to the new size
+    #image = image.resize((image.size[0] * 2, image.size[1] * 2))
+
+    if isinstance(image, Image.Image):
+        img = np.array(image)
+    
+    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.")
+
+    #width, height = img.shape[0], img.shape[1]
+
+    # 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,
+        'text_prompt': text_prompt,
+        'box_threshold': box_threshold,
+        'text_threshold': text_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)
+    duration = json_data['duration']
+    boxes = json_data['boxes']
+
+    # drow boxes on image
+    draw = ImageDraw.Draw(image)
+
+    for box in boxes:
+        left, top, right, bottom = box
+
+        if left <= 0: left = -LINE_WIDTH 
+        if top <= 0: top = top - LINE_WIDTH 
+        if right >= img.shape[0] - 1: right = img.shape[0] - 1 + LINE_WIDTH
+        if bottom >= img.shape[1] - 1: bottom = img.shape[1] - 1 + LINE_WIDTH
+
+        draw.rectangle([left, top, right, bottom], outline="red", width=LINE_WIDTH)
+    
+    return image, str(image.size), len(boxes), duration
+
+
+# Define example images and their true labels for users to choose from
+example_data = [
+    ["./demo/Pleiades_Neo_Tucson_USA.jpg", 'plane', 0.24, 0.24],
+    ["./demo/Pleiades_Neo_Tucson_USA.jpg", 'building', 0.24, 0.24],
+    ["./demo/Pleiades_Neo_Tucson_USA.jpg", 'tree', 0.24, 0.24],
+    ["./demo/two-dogs-with-a-stick.jpg", "dog", 0.25, 0.25],
+    ["./demo/airport01.jpg", "aircraft", 0.25, 0.25],
+    ["./demo/SPOT_Storage.jpg", "storage", 0.25, 0.25],
+    ["./demo/Satellite_Image_Marina_New_Zealand.jpg", "ship", 0.25, 0.25],
+    ["./demo/Pleiades_HD15_Miami_Marina.jpg", "ship", 0.25, 0.25],
+]
+
+# Define CSS for some elements
+css = """
+  .image-preview {
+    height: 820px !important; 
+    width: 800px !important;
+  } 
+"""
+TITLE = "Open 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, scale=1)
+            text_prompt = gr.Textbox(label="Text prompt")
+            run_button = gr.Button(value="Run", scale=0)
+            with gr.Accordion("Advanced options", open=True):
+                box_threshold = gr.Slider(label="Box threshold", minimum=0.0, maximum=1.0, value=0.24, step=0.01)
+                text_threshold = gr.Slider(label="Text threshold", minimum=0.0, maximum=1.0, value=0.24, step=0.01)
+                dimensions = gr.Textbox(label="Image size", interactive=False)
+                detections = gr.Number(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, width=800, height=800)
+
+    run_button.click(fn=predict_image, inputs=[input_image, text_prompt, box_threshold, text_threshold], outputs=[output_image, dimensions, detections, stopwatch])
+    gr.Examples(
+        examples=example_data,
+        inputs = [input_image, text_prompt, box_threshold, text_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>. The demonstration images are Pléiades \
+                images provided by CNES with distribution by Airbus DS. The model architecture and weights \
+                are provided <a href='https://github.com/IDEA-Research/GroundingDINO'>Grounding DINO</a>. \
+                This is a demonstration only. Please contact <a href='mailto:[email protected]'>me</a> \
+                for more information on how you could get access to a commercial model or API. </p>")
+
+demo.launch(
+    inline=False, 
+    show_api=False,
+    debug=False
+)

requirements.txt

@@ -0,0 +1,3 @@
+loguru
+ultralytics==8.1.18
+gradio==3.35.2