
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.models import model_from_json
from tensorflow.python.framework import ops
ops.reset_default_graph()
import h5py
from PIL import Image
from tensorflow.keras.preprocessing import image
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import matplotlib.pyplot as plt
import PIL
import numpy as np
#from vb100_utils import *
img = image.load_img("database/Training/Dog/1.jpg")
print('h5py version is {}'.format(h5py.__version__))
# 导入以保存好的.json CNN模型框架
json_file = open('./model.json')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
# 得到保存的.h5模型weights
loaded_model.load_weights('./model.h5')
opt = Adam(lr=0.00001, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.0)
loaded_model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='rmsprop')
#导入需要识别的图形进行识别
dir_path = 'database/Testing'
for i in os.listdir(dir_path ):
img = image.load_img(dir_path+'//'+i,target_size=(200,200))
plt.imshow(img)
plt.show()
X= image.img_to_array(img)
X= np.expand_dims(X,axis =0)
images = np.vstack([X])
val= loaded_model.predict(images)
if val == 1 :
print("DOG")
else:
print("CAT")