app

app.py

@@ -1,7 +1,109 @@
+import cv2
+import matplotlib.pyplot as plt
+import numpy as np
+from openvino.runtime import Core
 import gradio as gr
 
-def greet(name):
-    return "Hello " + name + "!!"
+##### 
+#Load pretrained model
+##### 
+ie = Core()
+model = ie.read_model(model="model/horizontal-text-detection-0001.xml")
+compiled_model = ie.compile_model(model=model, device_name="CPU")
+input_layer_ir = compiled_model.input(0)
+output_layer_ir = compiled_model.output("boxes")
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+##### 
+#Inference
+##### 
+def predict(img: np.ndarray) -> str:
+    # input: numpy array of image in RGB (see defaults for https://www.gradio.app/docs/#image)
+
+    # Text detection models expect an image in BGR format.
+    image = cv2.cvtColor(im_cv, cv2.COLOR_RGB2BGR)
+    # N,C,H,W = batch size, number of channels, height, width.
+    N, C, H, W = input_layer_ir.shape
+    # Resize the image to meet network expected input sizes.
+    resized_image = cv2.resize(image, (W, H))
+    # Reshape to the network input shape.
+    input_image = np.expand_dims(resized_image.transpose(2, 0, 1), 0)
+    
+    
+    # Create an inference request.
+    boxes = compiled_model([input_image])[output_layer_ir]
+    # Remove zero only boxes.
+    boxes = boxes[~np.all(boxes == 0, axis=1)]
+
+    result = convert_result_to_image(image, resized_image, boxes, conf_labels=False)
+      
+    plt.figure(figsize=(10, 6))
+    plt.axis("off")
+    plt.imshow(result)
+
+
+# For each detection, the description is in the [x_min, y_min, x_max, y_max, conf] format:
+# The image passed here is in BGR format with changed width and height. To display it in colors expected by matplotlib, use cvtColor function
+def convert_result_to_image(bgr_image, resized_image, boxes, threshold=0.3, conf_labels=True):
+    # Define colors for boxes and descriptions.
+    colors = {"red": (255, 0, 0), "green": (0, 255, 0)}
+
+    # Fetch the image shapes to calculate a ratio.
+    (real_y, real_x), (resized_y, resized_x) = bgr_image.shape[:2], resized_image.shape[:2]
+    ratio_x, ratio_y = real_x / resized_x, real_y / resized_y
+
+    # Convert the base image from BGR to RGB format.
+    rgb_image = cv2.cvtColor(bgr_image, cv2.COLOR_BGR2RGB)
+
+    # Iterate through non-zero boxes.
+    for box in boxes:
+        # Pick a confidence factor from the last place in an array.
+        conf = box[-1]
+        if conf > threshold:
+            # Convert float to int and multiply corner position of each box by x and y ratio.
+            # If the bounding box is found at the top of the image, 
+            # position the upper box bar little lower to make it visible on the image. 
+            (x_min, y_min, x_max, y_max) = [
+                int(max(corner_position * ratio_y, 10)) if idx % 2 
+                else int(corner_position * ratio_x)
+                for idx, corner_position in enumerate(box[:-1])
+            ]
+
+            # Draw a box based on the position, parameters in rectangle function are: image, start_point, end_point, color, thickness.
+            rgb_image = cv2.rectangle(rgb_image, (x_min, y_min), (x_max, y_max), colors["green"], 3)
+
+            # Add text to the image based on position and confidence.
+            # Parameters in text function are: image, text, bottom-left_corner_textfield, font, font_scale, color, thickness, line_type.
+            if conf_labels:
+                rgb_image = cv2.putText(
+                    rgb_image,
+                    f"{conf:.2f}",
+                    (x_min, y_min - 10),
+                    cv2.FONT_HERSHEY_SIMPLEX,
+                    0.8,
+                    colors["red"],
+                    1,
+                    cv2.LINE_AA,
+                )
+
+    return rgb_image
+
+##### 
+#Gradio Setup
+##### 
+
+title = "Text Detection"
+description = "Image Detection with OpenVino model"
+examples = ['test.jpg']
+interpretation='default'
+enable_queue=True
+
+gr.Interface(
+    fn=predict,
+    inputs=gr.inputs.Image(),
+    outputs=gr.outputs.Image(),
+    title=title,
+    description=description,
+    #examples=examples,
+    interpretation=interpretation,
+    enable_queue=enable_queue
+    ).launch()