20行代碼：Serverless架構下用Python輕鬆搞定圖像分類

圖像分類是人工智能領域的一個熱門話題，一樣在生產環境中也會常常會遇到相似的需求，那麼怎麼快速搭建一個圖像分類，或者圖像內容是別的API呢？

首先，給你們推薦一個圖像相關的庫：ImageAI

經過官方給的代碼，咱們能夠看到一個簡單的Demo：

from imageai.Prediction import ImagePrediction
import os
execution_path = os.getcwd()

prediction = ImagePrediction()
prediction.setModelTypeAsResNet()
prediction.setModelPath(os.path.join(execution_path, "resnet50_weights_tf_dim_ordering_tf_kernels.h5"))
prediction.loadModel()

predictions, probabilities = prediction.predictImage(os.path.join(execution_path, "1.jpg"), result_count=5 )
for eachPrediction, eachProbability in zip(predictions, probabilities):
    print(eachPrediction + " : " + eachProbability)

經過這個Demo咱們能夠考慮將這個模塊部署到雲函數：

首先，咱們在本地建立一個Python的項目：

mkdir imageDemo

而後新建文件：vim index.py

from imageai.Prediction import ImagePrediction
import os, base64, random

execution_path = os.getcwd()

prediction = ImagePrediction()
prediction.setModelTypeAsSqueezeNet()
prediction.setModelPath(os.path.join(execution_path, "squeezenet_weights_tf_dim_ordering_tf_kernels.h5"))
prediction.loadModel()


def main_handler(event, context):
    imgData = base64.b64decode(event["body"])
    fileName = '/tmp/' + "".join(random.sample('zyxwvutsrqponmlkjihgfedcba', 5))
    with open(fileName, 'wb') as f:
        f.write(imgData)
    resultData = {}
    predictions, probabilities = prediction.predictImage(fileName, result_count=5)
    for eachPrediction, eachProbability in zip(predictions, probabilities):
        resultData[eachPrediction] =  eachProbability
    return resultData

建立完成以後，咱們須要下載一下咱們所依賴的模型：

- SqueezeNet（文件大小：4.82 MB，預測時間最短，精準度適中）
- ResNet50 by Microsoft Research （文件大小：98 MB，預測時間較快，精準度高）
- InceptionV3 by Google Brain team （文件大小：91.6 MB，預測時間慢，精度更高）
- DenseNet121 by Facebook AI Research （文件大小：31.6 MB，預測時間較慢，精度最高）

咱們先用第一個SqueezeNet來作測試：

在官方文檔複製模型文件地址：

使用wget直接安裝：

wget https://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/squeezenet_weights_tf_dim_ordering_tf_kernels.h5

接下來，咱們就須要進行安裝依賴了，這裏面貌似安裝的內容蠻多的：

並且這些依賴有一些須要編譯的，這就須要咱們在centos + python2.7/3.6的版本下打包才能夠，這樣就顯得很是複雜，尤爲是mac/windows用戶，傷不起。

因此這時候，直接用我以前的打包網址：

直接下載解壓，而後放到本身的項目中：

最後，一步了，咱們建立serverless.yaml

imageDemo:
  component: "@serverless/tencent-scf"
  inputs:
    name: imageDemo
    codeUri: ./
    handler: index.main_handler
    runtime: Python3.6
    region: ap-guangzhou
    description: 圖像識別/分類Demo
    memorySize: 256
    timeout: 10
    events:
      - apigw:
          name: imageDemo_apigw_service
          parameters:
            protocols:
              - http
            serviceName: serverless
            description: 圖像識別/分類DemoAPI
            environment: release
            endpoints:
              - path: /image
                method: ANY

完成以後，執行咱們的sls --debug部署，部署過程當中會有掃碼的登錄，登錄以後等待便可，完成以後，咱們能夠複製生成的URL：

經過Python語言進行測試，url就是咱們剛纔複製的+/image：

import urllib.request
import base64

with open("1.jpg", 'rb') as f:
    base64_data = base64.b64encode(f.read())
    s = base64_data.decode()

url = 'http://service-9p7hbgvg-1256773370.gz.apigw.tencentcs.com/release/image'

print(urllib.request.urlopen(urllib.request.Request(
    url = url,
    data=s.encode("utf-8")
)).read().decode("utf-8"))

經過網絡搜索一張圖片，例如我找了這個：

獲得運行結果：

{"cheetah": 83.12643766403198, "Irish_terrier": 2.315458096563816, "lion": 1.8476998433470726, "teddy": 1.6655176877975464, "baboon": 1.5562783926725388}

將代碼修改一下，進行一下簡單的耗時測試：

import urllib.request
import base64, time

for i in range(0,10):
    start_time = time.time()
    with open("1.jpg", 'rb') as f:
        base64_data = base64.b64encode(f.read())
        s = base64_data.decode()

    url = 'http://service-hh53d8yz-1256773370.bj.apigw.tencentcs.com/release/test'

    print(urllib.request.urlopen(urllib.request.Request(
        url = url,
        data=s.encode("utf-8")
    )).read().decode("utf-8"))
    print("cost: ", time.time() - start_time)

輸出結果：

{"cheetah": 83.12643766403198, "Irish_terrier": 2.315458096563816, "lion": 1.8476998433470726, "teddy": 1.6655176877975464, "baboon": 1.5562783926725388}
cost:  2.1161561012268066
{"cheetah": 83.12643766403198, "Irish_terrier": 2.315458096563816, "lion": 1.8476998433470726, "teddy": 1.6655176877975464, "baboon": 1.5562783926725388}
cost:  1.1259253025054932
{"cheetah": 83.12643766403198, "Irish_terrier": 2.315458096563816, "lion": 1.8476998433470726, "teddy": 1.6655176877975464, "baboon": 1.5562783926725388}
cost:  1.3322770595550537
{"cheetah": 83.12643766403198, "Irish_terrier": 2.315458096563816, "lion": 1.8476998433470726, "teddy": 1.6655176877975464, "baboon": 1.5562783926725388}
cost:  1.3562259674072266
{"cheetah": 83.12643766403198, "Irish_terrier": 2.315458096563816, "lion": 1.8476998433470726, "teddy": 1.6655176877975464, "baboon": 1.5562783926725388}
cost:  1.0180821418762207
{"cheetah": 83.12643766403198, "Irish_terrier": 2.315458096563816, "lion": 1.8476998433470726, "teddy": 1.6655176877975464, "baboon": 1.5562783926725388}
cost:  1.4290671348571777
{"cheetah": 83.12643766403198, "Irish_terrier": 2.315458096563816, "lion": 1.8476998433470726, "teddy": 1.6655176877975464, "baboon": 1.5562783926725388}
cost:  1.5917718410491943
{"cheetah": 83.12643766403198, "Irish_terrier": 2.315458096563816, "lion": 1.8476998433470726, "teddy": 1.6655176877975464, "baboon": 1.5562783926725388}
cost:  1.1727900505065918
{"cheetah": 83.12643766403198, "Irish_terrier": 2.315458096563816, "lion": 1.8476998433470726, "teddy": 1.6655176877975464, "baboon": 1.5562783926725388}
cost:  2.962592840194702
{"cheetah": 83.12643766403198, "Irish_terrier": 2.315458096563816, "lion": 1.8476998433470726, "teddy": 1.6655176877975464, "baboon": 1.5562783926725388}
cost:  1.2248001098632812

這個數據，總體性能基本是在我能夠接受的範圍內。

至此，咱們經過Serveerless架構搭建的Python版本的圖像識別/分類小工具作好了。

---