2017-11-10 96 views
0

我使用python 3.6和Keras(2.0.9)在Tensorflow在Keras下载ResNet50产生 “SSL:CERTIFICATE_VERIFY_FAILED”

试图下载resnet50的训练的模型,但会遇到以下错误: 异常:URL抓取失败在https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels.h5:无 - [SSL:CERTIFICATE_VERIFY_FAILED]证书验证失败(_ssl.c:777)

以下是所使用的代码:

from keras.applications.resnet50 import ResNet50 
from keras.preprocessing import image 
from keras.applications.resnet50 import preprocess_input, decode_predictions 
import numpy as np 

model = ResNet50(weights='imagenet') 

img_path = 'elephant.jpg' 
img = image.load_img(img_path, target_size=(224, 224)) 
x = image.img_to_array(img) 
x = np.expand_dims(x, axis=0) 
x = preprocess_input(x) 
model.summary() 
preds = model.predict(x) 

print('Predicted:', decode_predictions(preds, top=3)[0]) 

回答