美文网首页
Keras.applications.models权重在线加载中

Keras.applications.models权重在线加载中

作者: 爱叫啥叫啥去 | 来源:发表于2019-11-21 17:33 被阅读0次

由于网速慢或网络中断原因导致keras加载vgg16等模型权重失败,导致无法使用,对于这个问题的直接解决方法是:删掉下载文件,再重新下载。

Github方法:

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’

相关文章

网友评论

      本文标题:Keras.applications.models权重在线加载中

      本文链接:https://www.haomeiwen.com/subject/shwtwctx.html