圖像分類是人工智能領域的一個熱門話題，同樣在生產環境中也會經常會遇到類似的需求，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，給大家推薦一個圖像相關的庫：ImageAI
通過官方給的代碼，我們可以看到一個簡單的Demo：
<code>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)/<code>
通過這個Demo我們可以考慮將這個模塊部署到雲函數：
首先，我們在本地創建一個Python的項目：
mkdir imageDemo
然後新建文件：vim index.py
<code>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/<code>
創建完成之後，我們需要下載一下我們所依賴的模型：
<code>- 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）/<code>
我們先用第一個SqueezeNet來做測試：
在官方文檔複製模型文件地址：
使用wget直接安裝：
<code>wget https://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/squeezenet_weights_tf_dim_ordering_tf_kernels.h5/<code>
接下來，我們就需要進行安裝依賴了，這裡面貌似安裝的內容蠻多的：
而且這些依賴有一些需要編譯的，這就需要我們在centos + python2.7/3.6的版本下打包才可以，這樣就顯得非常複雜，尤其是mac/windows用戶，傷不起。
所以這時候，直接用我之前的打包網址：
直接下載解壓，然後放到自己的項目中：
最後，一步了，我們創建serverless.yaml
<code>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/<code>
完成之後，執行我們的sls --debug部署，部署過程中會有掃碼的登陸，登陸之後等待即可，完成之後，我們可以複製生成的URL：
通過Python語言進行測試，url就是我們剛才複製的+/image：
<code>import urllib.request
import base64
with open("1.jpg", 'rb') as f:
base64_data = base64.b64encode(f.read())
s = base64_data.decode()
url = '生成的地址/image'
print(urllib.request.urlopen(urllib.request.Request(
url = url,
data=s.encode("utf-8")
)).read().decode("utf-8"))/<code>
通過網絡搜索一張圖片，例如我找了這個：
得到運行結果：
<code>{"cheetah": 83.12643766403198, "Irish_terrier": 2.315458096563816, "lion": 1.8476998433470726, "teddy": 1.6655176877975464, "baboon": 1.5562783926725388}/<code>將代碼修改一下，進行一下簡單的耗時測試：
<code>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 = '生成的地址/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)/<code>
輸出結果：
<code>{"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/<code> 這個數據，整體性能基本是在我可以接受的範圍內。
至此，我們通過Serveerless架構搭建的Python版本的圖像識別/分類小工具做好了。
分享到:
閱讀更多 GoServerless 的文章
