繁体   English   中英

如何在输入层和“模型作为层”之间放置层?

[英]How to put layers between an input layer and a “Model as layer”?

这有效:

img = Input(shape=(224,224,3))

efnet = EfficientNetB0(

    weights = 'noisy-student',
    include_top = False,
    pooling = None,
    classes = None

)
for layer in efnet.layers:
    layer.trainable = False

x = efnet(img)
# ... any number of layers ...
x = Dense(1)(x)

model = Model(inputs=img, outputs=x)

这不会(“图表已断开”):

img = Input(shape=(224,224,3))
img = Dropout(0.2)(img)
# ^ "Preprocessing" could be anything, Dropout is a simple example

efnet = EfficientNetB0(

    weights = 'noisy-student',
    include_top = False,
    pooling = None,
    classes = None

)
for layer in efnet.layers:
    layer.trainable = False

x = efnet(img)
# ... any number of layers ... 
x = Dense(1)(x)

model = Model(inputs=img, outputs=x)

两者之间的唯一区别是“预处理”。 为什么这不起作用,以及如何在输入和“模型作为层”之间放置中间层,如上所示?

(在 efnet 声明中指定 input_shape 和/或 input_tensor 无效。事实上,指定 input_tensor 会神秘地导致 efnet 权重无法加载,因为 efnet 显然有 131 层(???)而不是预期的 130。 )

我找到了解决该问题的方法,但我不知道为什么该修复会产生任何影响。

这有效:

img = Input(shape=(224,224,3))
x = Dropout(0.2)(img)
x = efnet(x) 
x = Dense(1)(x)
model = Model(inputs=img, outputs=x)

这不会:

img = Input(shape=(224,224,3))
img = Dropout(0.2)(img)
x = efnet(img) 
x = Dense(1)(x)
model = Model(inputs=img, outputs=x)

暂无
暂无

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM