基于 docker 和 Flask 的深度学习模型部署！

import osimport sys# Flaskfrom flask import Flask, redirect, url_for, request, render_template, Response, jsonify, redirectfrom werkzeug.utils import secure_filenamefrom gevent.pywsgi import WSGIServer# TensorFlow and tf.kerasimport tensorflow as tffrom tensorflow import kerasfrom tensorflow.keras.applications.imagenet_utils import preprocess_input, decode_predictionsfrom tensorflow.keras.models import load_modelfrom tensorflow.keras.preprocessing import image# Some utilitesimport numpy as npfrom util import base64_to_pil# Declare a flask appapp = Flask(__name__)# You can use pretrained model from Keras# Check https://keras.io/applications/# or https://www.tensorflow.org/api_docs/python/tf/keras/applicationsfrom tensorflow.keras.applications.mobilenet_v2 import MobileNetV2model = MobileNetV2(weights='imagenet')print('Model loaded. Check http://127.0.0.1:5000/')# Model saved with Keras model.save()MODEL_PATH = 'models/your_model.h5'# Load your own trained model# model = load_model(MODEL_PATH)# model._make_predict_function()          # Necessary# print('Model loaded. Start serving...')def model_predict(img, model):    img = img.resize((224, 224))    # Preprocessing the image    x = image.img_to_array(img)    # x = np.true_divide(x, 255)    x = np.expand_dims(x, axis=0)    # Be careful how your trained model deals with the input    # otherwise, it won't make correct prediction!    x = preprocess_input(x, mode='tf')    preds = model.predict(x)    return preds    @app.route('/', methods=['GET'])def index():    # Main page    return render_template('index.html')@app.route('/predict', methods=['GET', 'POST'])def predict():    if request.method == 'POST':        # Get the image from post request        img = base64_to_pil(request.json)        # Save the image to ./uploads        # img.save("./uploads/image.png")        # Make prediction        preds = model_predict(img, model)        # Process your result for human        pred_proba = "{:.3f}".format(np.amax(preds))    # Max probability        pred_class = decode_predictions(preds, top=1)   # ImageNet Decode        result = str(pred_class[0][0][1])               # Convert to string        result = result.replace('_', ' ').capitalize()                # Serialize the result, you can add additional fields        return jsonify(result=result, probability=pred_proba)    return None    if __name__ == '__main__':    # app.run(port=5002, threaded=False)  # Serve the app with gevent    http_server = WSGIServer(('0.0.0.0', 5000), app)    http_server.serve_forever()

# 指定Python环境FROM python:3.6-slim-stretch# 拷贝Python依赖库requirements文件到当前目录下ADD requirements.txt /# 安装依赖库RUN pip install -r /requirements.txt# 拷贝所有文件到app目录下ADD . /app# 指定app为工作目录WORKDIR /app# 声明端口EXPOSE 5000# docker容器启动CMD [ "python" , "app.py"]

Flask==1.1.1gevent==1.4.0h5py==2.10.0numpy==1.17.0Pillow==6.1.0tensorflow==2.3.1Werkzeug==0.16.0

docker build -t keras_flask_app .

docker run -it --rm -p 5000:5000 keras_flask_app