Yolo Model

app.py

@@ -0,0 +1,46 @@
+import gradio as gr
+from PIL import Image
+import tempfile
+import os
+import subprocess
+import glob
+
+
+def process_image(input_img):
+    # Create a temporary directory to store the input image
+    with tempfile.TemporaryDirectory() as temp_input_dir:
+        input_image_path = os.path.join(temp_input_dir, "input.jpg")
+        input_img.save(input_image_path)
+
+        # Create a temporary directory for the output image
+        with tempfile.TemporaryDirectory() as temp_output_dir:
+            # Command to run the YOLO model
+            command = f"yolo task=detect mode=predict model=best.pt conf=0.25 source={temp_input_dir} save=True"
+            subprocess.run(command, shell=True)
+
+           
+            # Get the most recent 'predict' folder in 'runs/detect'
+            list_of_dirs = glob.glob('runs/detect/predict*')
+            latest_dir = max(list_of_dirs, key=os.path.getctime)
+
+            # Assuming YOLO saves the output with the same name in the latest 'predict' folder
+            output_image_name = os.path.basename(input_image_path)
+            output_image_path = os.path.join(latest_dir, output_image_name)
+
+            if os.path.exists(output_image_path):
+                output_img = Image.open(output_image_path)
+                return output_img
+            else:
+                return "No output image found."
+
+# Define the Gradio interface
+demo = gr.Interface(
+    fn=process_image, 
+    inputs=gr.Image(type="pil"), 
+    outputs=gr.Image(type="pil"),
+    title="Object Detection with YOLO",
+    description="Upload an image and the YOLO model will detect objects."
+)
+
+# Launch the app
+demo.launch(share=True)

best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:299df2cc15fc2b7a9db5a8fe8344658098ecbb0cdbac632c119ad655857d5551
+size 22464291

requirements.txt

@@ -0,0 +1,6 @@
+numpy
+pandas
+ultralytics
+albumentations
+torchvision
+torch