Fix “AttributeError: module 'tensorflow' has no attribute 'get_default_graph'”

Question

我创建了一个 LSTM 模型，当运行它出现以下错误时：

 (...) File "/Users/myfolder/Desktop/Project-Deep-Learning-master/Flask_App/app.py", line 40, in <module>

    graph = tf.get_default_graph()

AttributeError: module 'tensorflow' has no attribute 'get_default_graph'

我在另一本 post 中读到过这方面的内容。可能是由我当前使用的 TensorFlow 版本引起的。

我将我的 TensorFlow 版本降级到最新的稳定版本 (1.13.1)。它没有解决问题，错误仍然存在。

我刚开始使用 keras 和机器学习，所以如果这很明显，我深表歉意。

我的代码是，app.py

from __future__ import division, print_function
# coding=utf-8
import sys
import os
import glob
import re
import numpy as np

# Keras
from keras.applications.imagenet_utils import preprocess_input, decode_predictions
from keras.models import load_model
from keras.preprocessing import image


from flask import Flask, redirect, url_for, request, render_template
from werkzeug.utils import secure_filename
from gevent.wsgi import WSGIServer

# Define a flask app
app = Flask(__name__)

# Model saved with Keras model.save()
MODEL_PATH = 'models/my_model.h5'

#Load your trained model
model = load_model(MODEL_PATH)
model._make_predict_function()          # Necessary to make everything ready to run on the GPU ahead of time
print('Model loaded. Start serving...')

# You can also use pretrained model from Keras
# Check https://keras.io/applications/
#from keras.applications.resnet50 import ResNet50
#model = ResNet50(weights='imagenet')
#print('Model loaded. Check http://127.0.0.1:5000/')


def model_predict(img_path, model):
    img = image.load_img(img_path, target_size=(50,50)) #target_size must agree with what the trained model expects!!

    # Preprocessing the image
    img = image.img_to_array(img)
    img = np.expand_dims(img, axis=0)


    preds = model.predict(img)
    pred = np.argmax(preds,axis = 1)
    return pred


@app.route('/', methods=['GET'])
def index():
    # Main page
    return render_template('index.html')


@app.route('/predict', methods=['GET', 'POST'])
def upload():
    if request.method == 'POST':
        # Get the file from post request
        f = request.files['file']

        # Save the file to ./uploads
        basepath = os.path.dirname(__file__)
        file_path = os.path.join(
            basepath, 'uploads', secure_filename(f.filename))
        f.save(file_path)

        # Make prediction
        pred = model_predict(file_path, model)
        os.remove(file_path)#removes file from the server after prediction has been returned

        # Arrange the correct return according to the model. 
        # In this model 1 is Pneumonia and 0 is Normal.
        str1 = 'Malaria Parasitized'
        str2 = 'Normal'
        if pred[0] == 0:
            return str1
        else:
            return str2
    return None


if __name__ == '__main__':
        app.run()
    #uncomment this section to serve the app locally with gevent at:  http://localhost:5000
    # Serve the app with gevent 
    #http_server = WSGIServer(('', 5000), app)
    #http_server.serve_forever()

Answer 1

您可以使用

from tensorflow.keras.applications.imagenet_utils 
import preprocess_input, decode_predictions
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing import image

这解决了我的代码问题。

Fix “AttributeError: module 'tensorflow' has no attribute 'get_default_graph'”

Fix “AttributeError: module 'tensorflow' has no attribute 'get_default_graph'”

python

keras

tensorflow

keras-layer

tf.keras