Python 向tensorflow.keras模型中间层提供输入
我正在尝试使用tensorflow.keras.applications EfficientNetB0实现hydranet体系结构。该体系结构的目标是将网络分为两部分(第一部分:主干,第二部分:头部)。然后,一个输入图像应该只向主干网馈送一次,并且它的输出应该被存储。之后,该输出应直接输入到头部(根据要分类的类的数量,可以有多个)。 最佳方法:Python 向tensorflow.keras模型中间层提供输入,python,tensorflow,keras,deep-learning,efficientnet,Python,Tensorflow,Keras,Deep Learning,Efficientnet,我正在尝试使用tensorflow.keras.applications EfficientNetB0实现hydranet体系结构。该体系结构的目标是将网络分为两部分(第一部分:主干,第二部分:头部)。然后,一个输入图像应该只向主干网馈送一次,并且它的输出应该被存储。之后,该输出应直接输入到头部(根据要分类的类的数量,可以有多个)。 最佳方法: 我不想为每个头部重新绘制整个模型 主干只能执行一次 如果已经查看此论坛帖子: 但是提出的解决方案要么需要对头部重新编码,要么不起作用 我尝试了以下方法:
from tensorflow.keras.applications import EfficientNetB0 as Net
from tensorflow.keras.models import Model
split_idx = 73
input_shape = (250, 250, 3) # use depth=3 because imagenet is trained on RGB images
model = Net(weights="imagenet", include_top = True)
# Approach 1:
# create the full network so we can train on it
model_backbone = keras.models.Model(inputs=model.input, outputs=model.layers[split_idx].output)
# create new model taking the output from backbone as input and creating final output of head
model_head = keras.models.Model(inputs=model.layers[split_idx].output,
outputs=model.layers[-1].output)
# Approach 2:
# create function for feeding input through backbone
# the function takes a normal input image as input and returns the output of the final backbone layer
create_backbone_output = K.function([model.layers[0].input], model.layers[split_idx].output)
# create function for feeding output of backbone through heads
create_heads_output = K.function([model.layers[split_idx].output],
model.output)
但当我尝试执行此操作时,两种方法都会出现“图形断开连接错误”:
WARNING:tensorflow:Functional model inputs must come from `tf.keras.Input` (thus holding past layer
metadata), they cannot be the output of a previous non-Input layer. Here, a tensor specified as input
to "model_5" was not an Input tensor, it was generated by layer block3b_drop.
Note that input tensors are instantiated via `tensor = tf.keras.Input(shape)`.
The tensor that caused the issue was: block3b_drop/Identity:0
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-33-64dd6f6430a1> in <module>
6 # create function for feeding output of backbone through heads
7 create_heads_output = K.function([model.layers[split_idx].output],
----> 8 model.output)
~\AppData\Roaming\Python\Python36\site-packages\tensorflow\python\keras\backend.py in
function(inputs,
outputs, updates, name, **kwargs)
4067 from tensorflow.python.keras import models # pylint: disable=g-import-not-at-top
4068 from tensorflow.python.keras.utils import tf_utils # pylint: disable=g-import-not-at-top
-> 4069 model = models.Model(inputs=inputs, outputs=outputs)
4070
4071 wrap_outputs = isinstance(outputs, list) and len(outputs) == 1
~\AppData\Roaming\Python\Python36\site-packages\tensorflow\python\training\tracking\base.py in
_method_wrapper(self, *args, **kwargs)
515 self._self_setattr_tracking = False # pylint: disable=protected-access
516 try:
--> 517 result = method(self, *args, **kwargs)
518 finally:
519 self._self_setattr_tracking = previous_value # pylint: disable=protected-access
~\AppData\Roaming\Python\Python36\site-packages\tensorflow\python\keras\engine\functional.py in
__init__(self, inputs, outputs, name, trainable, **kwargs)
118 generic_utils.validate_kwargs(kwargs, {})
119 super(Functional, self).__init__(name=name, trainable=trainable)
--> 120 self._init_graph_network(inputs, outputs)
121
122 @trackable.no_automatic_dependency_tracking
~\AppData\Roaming\Python\Python36\site-packages\tensorflow\python\training\tracking\base.py in
_method_wrapper(self, *args, **kwargs)
515 self._self_setattr_tracking = False # pylint: disable=protected-access
516 try:
--> 517 result = method(self, *args, **kwargs)
518 finally:
519 self._self_setattr_tracking = previous_value # pylint: disable=protected-access
~\AppData\Roaming\Python\Python36\site-packages\tensorflow\python\keras\engine\functional.py in
_init_graph_network(self, inputs, outputs)
202 # Keep track of the network's nodes and layers.
203 nodes, nodes_by_depth, layers, _ = _map_graph_network(
--> 204 self.inputs, self.outputs)
205 self._network_nodes = nodes
206 self._nodes_by_depth = nodes_by_depth
~\AppData\Roaming\Python\Python36\site-packages\tensorflow\python\keras\engine\functional.py in
_map_graph_network(inputs, outputs)
981 'The following previous layers '
982 'were accessed without issue: ' +
--> 983 str(layers_with_complete_input))
984 for x in nest.flatten(node.outputs):
985 computable_tensors.add(id(x))
ValueError: Graph disconnected: cannot obtain value for tensor
KerasTensor(type_spec=TensorSpec(shape=(None, 224, 224, 3), dtype=tf.float32, name='input_4'),
name='input_4', description="created by layer 'input_4'") at layer "rescaling_3". The following
previous layers were accessed without issue: []
警告:tensorflow:功能模型输入必须来自`tf.keras.Input`(因此保持在图层上
元数据),它们不能是前一个非输入层的输出。这里,指定为输入的张量
“model_5”不是一个输入张量,它是由层块3b_drop生成的。
注意,输入张量是通过“tensor=tf.keras.input(shape)”实例化的。
导致问题的张量为:block3b_drop/Identity:0
---------------------------------------------------------------------------
ValueError回溯(最近一次调用上次)
在里面
6#创建通过磁头馈送主干输出的功能
7创建\u heads\u output=K.function([model.layers[split\u idx].output],
---->8型号(输出)
中的~\AppData\Roaming\Python\Python36\site packages\tensorflow\Python\keras\backend.py
功能(输入,
输出、更新、名称,**kwargs)
4067来自tensorflow.python.keras导入模型#pylint:disable=g-import-not-at-top
4068从tensorflow.python.keras.utils导入tf_utils#pylint:disable=g-import-not-at-top
->4069模型=模型。模型(输入=输入,输出=输出)
4070
4071 wrap_输出=isinstance(输出,列表)和len(输出)=1
中的~\AppData\Roaming\Python\Python36\site packages\tensorflow\Python\training\tracking\base.py
_方法_包装器(self,*args,**kwargs)
515 self._self_setattr_tracking=False#pylint:disable=protected access
516试试:
-->517结果=方法(自身、*args、**kwargs)
518最后:
519 self._self_setattr_tracking=上一个值#pylint:disable=受保护访问
中的~\AppData\Roaming\Python\Python36\site packages\tensorflow\Python\keras\engine\functional.py
__初始(自我、输入、输出、名称、可培训、**kwargs)
118 generic_utils.validate_kwargs(kwargs,{})
119超级(功能,自我)。\uuuuu初始(名称=名称,可培训=可培训)
-->120自初始化图网络(输入、输出)
121
122@trackable.no\自动\依赖\跟踪
中的~\AppData\Roaming\Python\Python36\site packages\tensorflow\Python\training\tracking\base.py
_方法_包装器(self,*args,**kwargs)
515 self._self_setattr_tracking=False#pylint:disable=protected access
516试试:
-->517结果=方法(自身、*args、**kwargs)
518最后:
519 self._self_setattr_tracking=上一个值#pylint:disable=受保护访问
中的~\AppData\Roaming\Python\Python36\site packages\tensorflow\Python\keras\engine\functional.py
_初始图网络(自身、输入、输出)
202#跟踪网络的节点和层。
203个节点,节点按深度,层,映射图网络(
-->204自输入、自输出)
205自网络节点=节点
206 self.\u nodes\u by\u depth=nodes\u by\u depth
中的~\AppData\Roaming\Python\Python36\site packages\tensorflow\Python\keras\engine\functional.py
_映射图网络(输入、输出)
981“以下前几层”
982'已访问,没有问题:'+
-->983 str(带完整输入的图层))
984用于嵌套中的x。展平(节点输出):
985可计算的_张量。加(id(x))
ValueError:图形已断开连接:无法获取张量的值
KerasTensor(type_spec=TensorSpec(shape=(None,224,224,3),dtype=tf.float32,name='input_4'),
“重新缩放”层的name='input_4',description='由层'input_4'创建〕。以下
访问以前的层时没有问题:[]
我知道错误的根源是提供的张量不是输入张量。这个问题有什么解决办法吗?1。)这个模型不像你试图处理的那样循序渐进
->split_idx+1是添加另一层的添加操作,必须添加到第一个输出和第二个输入
block3b_drop (Dropout) (None, 28, 28, 40) 0 block3b_project_bn[0][0]
__________________________________________________________________________________________________
block3b_add (Add) (None, 28, 28, 40) 0 block3b_drop[0][0]
block3a_project_bn[0][0]
__________________________________________________________________________________________________
2.)添加所有需要的输入和给定的输出:
second_input1 = keras.Input(shape=model.layers[split_idx].output.shape[1:])
second_input2 = keras.Input(shape=model.get_layer(name='block3a_project_bn').output.shape[1:])
3.)重新连接模型的其余部分
在这里,您需要添加一些内容,但我会给您一些片段,让您开始:
for sequentially rewiring it it would be:
tmp = [second_input1,second_input2]
for l in range(split_idx+1, len(model.layers)):
layer = model.layers[l]
print(layer.name, layer.input)
tmp = layer(tmp)
在您的情况下,这还不够,您需要找到正确的输入,下面的snipped可以做到这一点。
找到正确的输入,要求输入到下一个输出(跟踪输出),然后通过图形进行处理
for l in model.layers:
# multiple inputs
if type(l.input) is list:
for li,lv in enumerate(l.input):
print('o ', li, lv.name)
else:
print('- ', l.input.name)
另一种便宜的方法是->将其另存为json,添加输入节点,删除未使用的节点。加载新的json文件,在这种情况下,您不需要重新布线