def load_model(file_path):
""" Load a pysster.Model object.
Parameters
----------
file_path : str
A file containing a pickled pysster.Model object (file_path.h5 must also exist, see save_model()).
Returns
-------
model : pysster.Model
A Model object.
"""
from pysster.Model import Model
from keras.models import load_model as load_keras
if not os.path.exists(file_path):
raise RuntimeError("Path not found.")
if not os.path.exists("{}.h5".format(file_path)):
raise RuntimeError("HDF5 file not found.")
with gzip.open(file_path, "rb") as handle:
params = pickle.load(handle)
model = Model(params, None)
model.model = load_keras("{}.h5".format(file_path))
return model
from keras.models import load_keras
from scikit-image import transform
import numpy as np
from keras.preprocessing.image import load_img
from flask import Flask, request, render_template , jsonify
app = Flask(__name__)
covid = load_keras('Covid19.h5')
def Load_Images(img):
pred_img = np.array(img).astype('float32')/255
pred_img = transform.resize(pred_img,(200,200,3))
pred_img = np.expand_dims(pred_img,axis=0)
return pred_img
@app.route('/')
def index():
print('Working')
@app.route('/CovidRequest', methods=['POST'])
def post():
imagefile = request.files.get('imagefile', '')
Image_to_pred = load_img(imagefile)
Image_to_pred = Load_Images(Image_to_pred)
prediction = np.argmax(covid.predict(Image_to_pred))
if (prediction == 0):
return jsonify({'prediction':'Non Informative Data'})
elif (prediction == 1):
return jsonify({'prediction':'Negative'})