Gradio 最快创建Web 界面部署到服务器并演示机器学习模型，本文提供教学案例以及部署方法，避免使用繁琐的django

最近学习hugging face里面的物体检测模型，发现一个方便快捷的工具！

Gradio 是通过友好的 Web 界面演示机器学习模型的最快方式，以便任何人都可以在任何地方使用它！

一、核心优势：

使用这个开发这种演示机器学习模型的web界面会比django会快上不少！

只需要一个py文件即可实现模型界面创建，部署模型到服务器及时间响应所有功能。

二、重要参考连接：

官网如下：

Gradio

别人的部署到hugging face的space服务器案例如下：（可全网任意访问-）

https://huggingface.co/spaces/ClassCat/DETR-Object-Detection

案例对应的代码如下：

https://huggingface.co/spaces/ClassCat/DETR-Object-Detection/tree/main

三、自己本地服务器部署的案例

自己的物检测及体识别的代码（亲测成功）：

import torch
from transformers import pipeline
 
from PIL import Image
 
import matplotlib.pyplot as plt
import matplotlib.patches as patches
 
from random import choice
import io
 
detector50 = pipeline(model="facebook/detr-resnet-50")#自动下载模型，大约200MB
 
# detector101 = pipeline(model="facebook/detr-resnet-101")
 
 
import gradio as gr
 
COLORS = ["#ff7f7f", "#ff7fbf", "#ff7fff", "#bf7fff",
            "#7f7fff", "#7fbfff", "#7fffff", "#7fffbf",
            "#7fff7f", "#bfff7f", "#ffff7f", "#ffbf7f"]
 
fdic = {
    "family" : "Arial",
    "style" : "italic",
    "size" : 15,
    "color" : "yellow",
    "weight" : "bold"
}
 
 
def get_figure(in_pil_img, in_results):
    plt.figure(figsize=(16, 10))
    plt.imshow(in_pil_img)
    #pyplot.gcf()
    ax = plt.gca()
 
    for prediction in in_results:
        selected_color = choice(COLORS)
 
        x, y = prediction['box']['xmin'], prediction['box']['ymin'],
        w, h = prediction['box']['xmax'] - prediction['box']['xmin'], prediction['box']['ymax'] - prediction['box']['ymin']
 
        ax.add_patch(plt.Rectangle((x, y), w, h, fill=False, color=selected_color, linewidth=3))
        ax.text(x, y, f"{prediction['label']}: {round(prediction['score']*100, 1)}%", fontdict=fdic)
 
    plt.axis("off")
 
    return plt.gcf()
 
 
 
 
 
def infer(model, in_pil_img):
 
    results = None
    if model == "detr-resnet-101":
        results = detector101(in_pil_img)
    else:
        results = detector50(in_pil_img)
 
    figure = get_figure(in_pil_img, results)
 
    buf = io.BytesIO()
    figure.savefig(buf, bbox_inches='tight')
    buf.seek(0)
    output_pil_img = Image.open(buf)
 
    return output_pil_img
 
 
with gr.Blocks(title="DETR Object Detection - ClassCat",
                    css=".gradio-container {background:lightyellow;}"
               ) as demo:
    #sample_index = gr.State([])
 
    gr.HTML("""
DETR Object Detection
""")
 
    gr.HTML("""
1. Select a model.
""")
 
    model = gr.Radio(["detr-resnet-50", "detr-resnet-101"], value="detr-resnet-50", label="Model name")
 
    gr.HTML("""
""")
    gr.HTML("""
2-a. Select an example by clicking a thumbnail below.
""")
    gr.HTML("""
2-b. Or upload an image by clicking on the canvas.
""")
 
    with gr.Row():
        input_image = gr.Image(label="Input image", type="pil")
        output_image = gr.Image(label="Output image with predicted instances", type="pil")
 
    gr.Examples(['samples/cats.jpg', 'samples/detectron2.png'], inputs=input_image)
 
    gr.HTML("""
""")
    gr.HTML("""
3. Then, click "Infer" button to predict object instances. It will take about 10 seconds (on cpu)
""")
 
    send_btn = gr.Button("Infer")
    send_btn.click(fn=infer, inputs=[model, input_image], outputs=[output_image])
 
    gr.HTML("""
""")
    gr.HTML("""
Reference参考链接
""")
    gr.HTML("""
""")
    gr.HTML("""
Hands-on tutorial for DETR""")