一个例子:

    print("Loading vgg19 weights...")
 
    vgg_model = VGG19(include_top=False, weights='imagenet')
 
    from_vgg = dict()  # 因为模型定义中的layer的名字与原始vgg名字不同,所以需要调整
    from_vgg['conv1_1'] = 'block1_conv1'
    from_vgg['conv1_2'] = 'block1_conv2'
    from_vgg['conv2_1'] = 'block2_conv1'
    from_vgg['conv2_2'] = 'block2_conv2'
    from_vgg['conv3_1'] = 'block3_conv1'
    from_vgg['conv3_2'] = 'block3_conv2'
    from_vgg['conv3_3'] = 'block3_conv3'
    from_vgg['conv3_4'] = 'block3_conv4'
    from_vgg['conv4_1'] = 'block4_conv1'
    from_vgg['conv4_2'] = 'block4_conv2'
 
    for layer in model.layers:
      if layer.name in from_vgg:
        vgg_layer_name = from_vgg[layer.name]
        layer.set_weights(vgg_model.get_layer(vgg_layer_name).get_weights())
        print("Loaded VGG19 layer: " + vgg_layer_name)
densenet.load_weights('model/densenet_weight/densenet_bottom.h5')
# densenet.save_weights('densenet_bottom.h5')
 
# print(densenet.weights)# 获得模型所有权值
t=densenet.get_layer('densenet_conv1/bn')
print(t)
print(densenet.get_weights()[2])

以上这篇keras获得某一层或者某层权重的输出实例就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。

广告合作:本站广告合作请联系QQ:858582 申请时备注:广告合作(否则不回)
免责声明:本站资源来自互联网收集,仅供用于学习和交流,请遵循相关法律法规,本站一切资源不代表本站立场,如有侵权、后门、不妥请联系本站删除!