[英]How to break one Functional Resnet50 model into multiple layer
我使用以下方法創建了 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總結:
Layer (type) Output Shape Param #
=================================================================
input_image (InputLayer) [(None, 256, 256, 3)] 0
resnet50 (Functional) (None, 8, 8, 2048) 23587712
=================================================================
后來,我意識到我需要像這樣訪問一些層:
Resmodel.layers[4].output
但是,我得到了:
IndexError: list index out of range
是否可以將 Resnet50 功能性 model 分解為多重層或訪問 model 的某個層。
嘗試這個
model.layers[1].layers[4]
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.