# D:/workplace/python
# -*- coding: utf-8 -*-
# @File  :test.py
# @Author:Guido    LuXiaohao
# @Date  :2020/4/8
# @Software:PyCharm

import cv2
import time
import os
import numpy as np
import tensorflow as tf

from keras.preprocessing.image import img_to_array
from keras.models import load_model
from keras.backend.tensorflow_backend import set_session

os.environ["CUDA_VISIBLE_DEVICES"] = "0"  # 指定GPU

config = tf.ConfigProto()
config.gpu_options.allow_growth = True  # 按需
set_session(tf.Session(config=config))


def predict(image_path, model_path, norm_size=128):
    # load the trained convolutional neural network
    print("[INFO] loading network...")
    model = load_model(model_path)
    # load the image
    image = cv2.imdecode(np.fromfile(image_path, dtype=np.uint8), -1)
    # pre-process the image for classification
    image = cv2.resize(image, (norm_size, norm_size))
    image = image.astype("float") / 255.0
    image = img_to_array(image)
    image = np.expand_dims(image, axis=0)

    # classify the input image
    result = model.predict(image)[0]
    proba = np.max(result)
    label = str(np.where(result == proba)[0])
    label = "{}: {:.2f}%".format(label, proba * 100)
    print(label)

def resize_LongestMaxSize(image, norm_size):

    image_height = image.shape[0]
    image_width = image.shape[1]

    if image_height > image_width:
        image = cv2.resize(image, (int(norm_size * image_width / image_height), norm_size))
        pad_len = int((norm_size - norm_size * image_width / image_height) / 2)
        image = np.pad(image, ((0, 0), (pad_len, pad_len), (0, 0)), constant_values=0)
        image = cv2.resize(image, (norm_size, norm_size))
    else:
        image = cv2.resize(image, (norm_size, int(norm_size * image_height / image_width)))
        pad_len = int((norm_size - norm_size * image_height / image_width) / 2)
        print(pad_len)
        image = np.pad(image, ((pad_len, pad_len), (0, 0), (0, 0)), constant_values=0)
        image = cv2.resize(image, (norm_size, norm_size))

    return image