update app.py

app.py

@@ -0,0 +1,65 @@
+import cv2
+import numpy as np
+import gradio as gr
+import matplotlib.pyplot as plt
+from transformers import pipeline
+
+
+model = pipeline("object-detection", "facebook/detr-resnet-50")  #loading model
+
+#render function
+
+def render_results(raw_image, model_output):
+
+  raw_image = np.array(raw_image)
+
+  for detection in model_output:
+      label = detection['label']
+      score = detection['score']
+      box = detection['box']
+      xmin, ymin, xmax, ymax = box['xmin'], box['ymin'], box['xmax'], box['ymax']
+
+      #Drawing the bounding box
+      cv2.rectangle(raw_image, (xmin, ymin), (xmax, ymax), (0, 255, 0), 2)
+
+      #Puting label and score near the bounding box
+      cv2.putText(raw_image, f"{label}: {score:.2f}", (xmin, ymin - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
+  return raw_image
+
+
+
+def get_object_counts(detections):  ##to get count of object detected in the image
+    object_counts = {}
+    for detection in detections:
+        label = detection['label']
+        if label in object_counts:
+            object_counts[label] += 1
+        else:
+            object_counts[label] = 1
+
+    return object_counts
+
+def generate_output_text(object_counts):  ##to get the output string
+    output_text = "In this image there are"
+    for label, count in object_counts.items():
+        output_text += f" {count} {label},"
+    output_text = output_text.rstrip(',') + "."
+    return output_text
+
+
+
+def main(pil_image):
+  pipeline_output = model(pil_image)  #model output
+  processed_image = render_results(pil_image, pipeline_output)  ##process image by drawing bounding boxes
+  output_text = generate_output_text(get_object_counts(pipeline_output))  ##output string
+
+  return processed_image, output_text
+
+
+demo = gr.Interface(
+    fn = main,
+    inputs = gr.Image(label = "Input Image", type = "pil"),
+    outputs = [gr.Image(label = "Modle output Predictions", type = "numpy"), gr.Text(label="Output Text")]
+)
+
+demo.launch()