网络中断原因导致keras加载vgg16等模型权重失败, 
直接解决方法是:删掉下载文件,再重新下载

 

Windows-weights路径

C:\Users\你的用户名\.keras\models

Linux-weights路径

.keras/models/ 
注意: linux中 带点号的文件都被隐藏了,需要查看hidden文件才能显示

Keras-Github-教程 
https://github.com/fchollet/deep-learning-models 
原始权重下载地址 
https://github.com/fchollet/deep-learning-models/releases 
tf模型权重百度云下载地址 
http://pan.baidu.com/s/1dE9giOD

VGG16:

WEIGHTS_PATH = 
https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels.h5’ 
WEIGHTS_PATH_NO_TOP = 
https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5

VGG19:

TF_WEIGHTS_PATH = 
https://github.com/fchollet/deep-learning-models/releases/download/v0.4/xception_weights_tf_dim_ordering_tf_kernels.h5’ 
TF_WEIGHTS_PATH_NO_TOP = 
https://github.com/fchollet/deep-learning-models/releases/download/v0.4/xception_weights_tf_dim_ordering_tf_kernels_notop.h5

RESNET50:

WEIGHTS_PATH = 
https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels.h5’ 
WEIGHTS_PATH_NO_TOP = 
https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5

INCEPTIONS_V3:

WEIGHTS_PATH = 
https://github.com/fchollet/deep-learning-models/releases/download/v0.5/inception_v3_weights_tf_dim_ordering_tf_kernels.h5’ 
WEIGHTS_PATH_NO_TOP = 
https://github.com/fchollet/deep-learning-models/releases/download/v0.5/inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5

XCEPTION:

TF_WEIGHTS_PATH = 
https://github.com/fchollet/deep-learning-models/releases/download/v0.4/xception_weights_tf_dim_ordering_tf_kernels.h5’ 
TF_WEIGHTS_PATH_NO_TOP = 
https://github.com/fchollet/deep-learning-models/releases/download/v0.4/xception_weights_tf_dim_ordering_tf_kernels_notop.h5