gradio web ui

README.md

@@ -2,6 +2,8 @@
 <img src="https://user-images.githubusercontent.com/26833433/98699617-a1595a00-2377-11eb-8145-fc674eb9b1a7.jpg" width="1000"></a>
 &nbsp
 
+[![Gradio](gradio.png)](https://gradio.app/g/AK391/yolov5)
+
 <a href="https://github.com/ultralytics/yolov5/actions"><img src="https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg" alt="CI CPU testing"></a>
 
 This repository represents Ultralytics open-source research into future object detection methods, and incorporates lessons learned and best practices evolved over thousands of hours of training and evolution on anonymized client datasets. **All code and models are under active development, and are subject to modification or deletion without notice.** Use at your own risk.

demo.py

@@ -0,0 +1,36 @@
+import torch
+from PIL import Image
+from torchvision import transforms
+import gradio as gr
+from io import BytesIO
+import base64
+import os
+
+
+# Model
+model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)
+
+def yolo(img):
+  img.save("test_image_hack.png")
+  img = Image.open("test_image_hack.png")
+  results = model(img)  # inference
+  os.remove("test_image_hack.png")
+
+  results.imgs # array of original images (as np array) passed to model for inference
+  results.render()  # updates results.imgs with boxes and labels
+  for img in results.imgs:
+    return Image.fromarray(img)
+
+
+inputs =  gr.inputs.Image(type='pil', label="Original Image")
+outputs = gr.outputs.Image(type="pil",label="Output Image")
+
+title = "YOLOv5"
+description = "demo for YOLOv5 which takes in a single image for object detection. To use it, simply upload your image, or click one of the examples to load them. Read more at the links below."
+article = "<a href='https://github.com/ultralytics/yolov5'>Github Repo</a></p>"
+
+examples = [
+    ['bird.jpg'],
+    ['fox.jpg']
+]
+gr.Interface(yolo, inputs, outputs, title=title, description=description, article=article, examples=examples).launch(debug=True)

detect.py

@@ -110,7 +110,7 @@ def detect(save_img=False):
 
                     if save_img or view_img:  # Add bbox to image
                         label = f'{names[int(cls)]} {conf:.2f}'
-                        plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3)
+                        plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=9)
 
             # Print time (inference + NMS)
             print(f'{s}Done. ({t2 - t1:.3f}s)')

utils/plots.py

@@ -54,7 +54,7 @@ def butter_lowpass(cutoff, fs, order):
     return filtfilt(b, a, data)  # forward-backward filter
 
 
-def plot_one_box(x, img, color=None, label=None, line_thickness=3):
+def plot_one_box(x, img, color=None, label=None, line_thickness=9):
     # Plots one bounding box on image img
     tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1  # line/font thickness
     color = color or [random.randint(0, 255) for _ in range(3)]