keras - layers_by_depth和layers之间的区别

Question

我想要计算模型层的数量。我使用两种方法：

len(model.layers)

和

len(model.layers_by_depth)

但是我得到了不同的结果。layers_by_depth和layers有什么区别？谢谢!

Answer 1

model.layers将为您提供所有层的列表。它们与您添加它们的顺序基本一致。

model.layers_by_depth (在较新的版本中似乎已被删除)将为您提供一个字典，其中包含每个深度(关键点)的图层列表。

在这里，图层将按深度分组。

Answer 2

您可以阅读source code以了解layers_by_depth是如何构建的：

# Build a dict {depth: list of layers with this depth}
layers_by_depth = {}
for layer, depth in layers_depths.items():
    if depth not in layers_by_depth:
        layers_by_depth[depth] = []
layers_by_depth[depth].append(layer)

self.layers是如何构建的：

# Set self.layers and self.layers_by_depth.

layers = []
for depth in depth_keys:
    layers_for_depth = layers_by_depth[depth]
    # Container.layers needs to have a deterministic order:
    # here we order them by traversal order.
    layers_for_depth.sort(key=lambda x: layer_indices[x])
    for layer in layers_for_depth:
        layers.append(layer)
self.layers = layers
self.layers_by_depth = layers_by_depth