RK3588 AI 应用开发 （FCN-语义分割）【玩转华为云】

RK3588 AI 应用开发 （FCN-语义分割）

一、模型训练与转换

FCN（全卷积网络，Fully Convolutional Networks）是用于语义分割任务的一种深度学习模型架构，引入了跳跃结构（Skip Architecture），通过融合浅层和深层的特征图，保留更多的细节信息，提升分割精度。此外，FCN还利用多尺度上下文聚合，捕捉不同层级的特征，增强了对不同大小目标的识别能力。FCN的成功推动了语义分割领域的发展，成为后续许多先进模型的基础。

模型的训练与转换教程已经开放在AI Gallery中，其中包含训练数据、训练代码、模型转换脚本。

在ModelArts的Notebook环境中训练后，再转换成对应平台的模型格式：onnx格式可以用在Windows设备上，RK系列设备上需要转换为rknn格式。

二、应用开发

1. 开发 Gradio 界面

import cv2
import json
import base64
import requests
import numpy as np
import gradio as gr


def test_image(image_path):
    try:
        image_bgr = cv2.imread(image_path)
        image_string = cv2.imencode('.jpg', image_bgr)[1].tobytes()
        image_base64 = base64.b64encode(image_string).decode('utf-8')
        params = {"image_base64": image_base64}

        response = requests.post(f'http://{ip}:{port}{url}', data=json.dumps(params),
                                headers={"Content-Type": "application/json"})
        
        if response.status_code == 200:
            image_base64 = response.json().get("image_base64")
            image_binary = base64.b64decode(image_base64)
            image_array = np.frombuffer(image_binary, dtype=np.uint8)
            image_rgb = cv2.imdecode(image_array, cv2.IMREAD_COLOR)
        else:
            image_rgb = None

    except Exception as e:
        return None
    else:    
        return image_rgb
    

if __name__ == "__main__":
    port = 8000
    ip = "127.0.0.1"
    url = "/v1/FCN"

    demo = gr.Interface(fn=test_image, inputs=gr.Image(type="filepath"), outputs=["image"], title="FCN 果蔬病虫害分割")
    demo.launch(share=False, server_port=3000)

/home/orangepi/miniconda3/envs/python-3.10.10/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm
* Running on local URL:  http://127.0.0.1:3000
* To create a public link, set `share=True` in `launch()`.

2. 编写推理代码

class FCN:
    def __init__(self, model_path):
        self.num_classes = 117
        self.rknn_lite = RKNNLite()
        self.rknn_lite.load_rknn(model_path)
        self.rknn_lite.init_runtime(core_mask=RKNNLite.NPU_CORE_0_1_2)
        self.color_list = np.random.randint(0, 255, size=(self.num_classes, 3), dtype=np.uint8).tolist()  
        

    def preprocess(self, image):
        image = image[:, :, ::-1]  
        image = cv2.resize(image, (224, 224)) 
        return np.expand_dims(image, axis=0)

    
    def rknn_infer(self, data):
        outputs = self.rknn_lite.inference(inputs=[data])
        return outputs[0]
    
    
    def post_process(self, pred):
        feat = pred.squeeze()
        return np.argmax(feat, axis=-1).astype(np.uint8)
    
    
    def predict(self, image):
        # 图像预处理
        data = self.preprocess(image)
        # 模型推理
        pred = self.rknn_infer(data)
        # 模型后处理
        feat = self.post_process(pred)
        # 生成图像分割结果
        canv = np.zeros_like(image)
        mask = cv2.resize(feat, image.shape[:2][::-1], interpolation=cv2.INTER_NEAREST)
        for i in range(1, self.num_classes):
            canv[mask==i] = self.color_list[i]
        return cv2.addWeighted(image[..., ::-1], 0.5, canv, 0.5, 0)

    def release(self):
        self.rknn_lite.release()

3. 图片批量预测

import os
import cv2
import numpy as np
import matplotlib.pyplot as plt
from rknnlite.api import RKNNLite

model = FCN('model/FCN.rknn')

for image in os.listdir("image"):
    image = cv2.imread(os.path.join("image", image))
    image = model.predict(image)
    plt.imshow(image)
    plt.axis('off')
    plt.show()
    
model.release()

4. 创建 Flask 服务

import cv2
import base64
import numpy as np
from rknnlite.api import RKNNLite
from flask import Flask, request, jsonify
from flask_cors import CORS

app = Flask(__name__)
CORS(app)

@app.route('/v1/FCN', methods=['POST'])
def inference():
    data = request.get_json()
    image_base64 = data.get("image_base64")
    image_binary = base64.b64decode(image_base64)
    image_array = np.frombuffer(image_binary, dtype=np.uint8)
    image_bgr = cv2.imdecode(image_array, cv2.IMREAD_COLOR)

    image_rgb = model.predict(image_bgr)

    image_string = cv2.imencode('.jpg', image_rgb)[1].tobytes()
    image_base64 = base64.b64encode(image_string).decode('utf-8')

    return jsonify({
        "image_base64": image_base64
    }), 200

if __name__ == '__main__':
    model = FCN('model/FCN.rknn')
    app.run(host='0.0.0.0', port=8000) 
    model.release()

W rknn-toolkit-lite2 version: 2.3.2
I RKNN: [00:06:51.738] RKNN Runtime Information: librknnrt version: 1.4.0 (a10f100eb@2022-09-09T09:07:14)
I RKNN: [00:06:51.738] RKNN Driver Information: version: 0.9.6
I RKNN: [00:06:51.739] RKNN Model Information: version: 1, toolkit version: 1.4.0-22dcfef4(compiler version: 1.4.0 (3b4520e4f@2022-09-05T12:50:09)), target: RKNPU v2, target platform: rk3588, framework name: TFLite, framework layout: NHWC
 * Serving Flask app '__main__'
 * Debug mode: off
WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead.
 * Running on all addresses (0.0.0.0)
 * Running on http://127.0.0.1:8000
 * Running on http://192.168.3.50:8000
Press CTRL+C to quit
127.0.0.1 - - [02/May/2025 00:07:17] "POST /v1/FCN HTTP/1.1" 200 -
127.0.0.1 - - [02/May/2025 00:07:24] "POST /v1/FCN HTTP/1.1" 200 -
127.0.0.1 - - [02/May/2025 00:07:31] "POST /v1/FCN HTTP/1.1" 200 -
127.0.0.1 - - [02/May/2025 00:07:39] "POST /v1/FCN HTTP/1.1" 200 -

5. 上传图片预测

三、小结

本章介绍了基于RK3588平台使用FCN模型进行语义分割的AI应用开发全流程，包括模型训练与转换、Gradio界面开发、推理代码编写、批量预测实现及Flask服务部署。通过该流程，开发者可实现高效的图像分割任务，并在本地或云端进行预测和展示。