Upload 8 files

Damage_Vehicle_Y5.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2afa57d9aba09f8577fd4a4e8f079c6d7566daf401fab314900d1ae96a7c2aa3
+size 14431485

app.py

@@ -0,0 +1,83 @@
+import gradio as gr
+from gradio.outputs import Label
+import cv2
+import requests
+import os
+import numpy as np
+
+from ultralytics import YOLO
+import yolov5
+
+# Image download
+# file_urls = [
+# ]
+
+# def download_file(url, save_name):
+#     url = url
+#     if not os.path.exists(save_name):
+#         file = requests.get(url)
+#         open(save_name, 'wb').write(file.content)
+
+# for i, url in enumerate(file_urls):    
+#     download_file(
+#         file_urls[i],
+#         f"image_{i}.jpg"
+#     )
+
+# Function for inference
+def yolov5_inference(
+    image: gr.inputs.Image = None,
+    model_path: gr.inputs.Dropdown = None,
+    image_size: gr.inputs.Slider = 640,
+    conf_threshold: gr.inputs.Slider = 0.25,
+    iou_threshold: gr.inputs.Slider = 0.45 ):
+
+    # Loading Yolo V5 model
+    model = yolov5.load(model_path, device="cpu")
+
+    # Setting model configuration 
+    model.conf = conf_threshold
+    model.iou = iou_threshold
+
+    # Inference
+    results = model([image], size=image_size)
+
+    # Cropping the predictions    
+    crops = results.crop(save=False)
+    img_crops = []
+    for i in range(len(crops)):
+        img_crops.append(crops[i]["im"][..., ::-1])
+    return results.render()[0], img_crops
+        
+# gradio Input
+inputs = [
+    gr.inputs.Image(type="pil", label="Input Image"),
+    gr.inputs.Dropdown(["Damage_Vehicle_Y5.pt","yolov5s.pt", "yolov5m.pt", "yolov5l.pt", "yolov5x.pt"], label="Model", default = 'Crime_Y5.pt'),
+    gr.inputs.Slider(minimum=320, maximum=1280, default=640, step=32, label="Image Size"),
+    gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.25, step=0.05, label="Confidence Threshold"),
+    gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.45, step=0.05, label="IOU Threshold"),
+]
+
+# gradio Output
+outputs = gr.outputs.Image(type="filepath", label="Output Image")
+outputs_crops = gr.Gallery(label="Object crop")
+
+title = "Vehicle damage detection"
+
+# gradio examples: "Image", "Model", "Image Size", "Confidence Threshold", "IOU Threshold"
+examples = [['1.jpg', 'Damage_Vehicle_Y5.pt', 640, 0.35, 0.45]
+          ,['2.jpg', 'Damage_Vehicle_Y5.pt', 640, 0.35, 0.45]
+          ,['3.jpg', 'Damage_Vehicle_Y5.pt', 640, 0.35, 0.45]]
+
+# gradio app launch
+demo_app = gr.Interface(
+    fn=yolov5_inference,
+    inputs=inputs,
+    outputs=[outputs,outputs_crops],
+    title=title,
+    examples=examples,
+    cache_examples=True,
+    live=True,
+    theme='huggingface',
+)
+demo_app.launch(debug=True, enable_queue=True, width=50, height=50)

requirements.txt

@@ -0,0 +1,8 @@
+torch
+gradio==3.4.0
+opencv-python
+numpy<1.24
+ultralytics
+yolov5
+
+

yolov5l.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f603b7354c25454d1270663a14d8ddc1eea98e5eebc1d84ce0c6e3150fa155f
+size 93622629

yolov5s.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3b748c1e592ddd8868022e8732fde20025197328490623cc16c6f24d0782ee
+size 14808437