[英]How to break one Functional Resnet50 model into multiple layer
I created Resnet50 using:我使用以下方法创建了 Resnet50:
base_model = tf.keras.applications.ResNet50(include_top=False, weights=None, input_shape=(224, 224, 3))
base_model.trainable = True
inputs = Input((224, 224, 3))
h = base_model(inputs, training=True)
model = Model(inputs, projection_3)
model summary: model总结:
Layer (type) Output Shape Param #
=================================================================
input_image (InputLayer) [(None, 256, 256, 3)] 0
resnet50 (Functional) (None, 8, 8, 2048) 23587712
=================================================================
Later, I realized I need to access some layer like this:后来,我意识到我需要像这样访问一些层:
Resmodel.layers[4].output
However, I got:但是,我得到了:
IndexError: list index out of range
Is there away to break the Resnet50 funcational model into mutpile layer OR there away to access a certain layer of the model .是否可以将 Resnet50 功能性 model 分解为多重层或访问 model 的某个层。
try this尝试这个
model.layers[1].layers[4] model.layers[1].layers[4]
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.