如何在keras中用占位符包装张量流图

Question

我有一个带有占位符操作作为输入的张量流图（存储在一个 protobuffer 文件中）。我想将此图包装为 keras 层或模型。

这是一个例子：

with tf.Graph().as_default() as gf:
    x = tf.placeholder(tf.float32, shape=(None, 123), name='x')
    c = tf.constant(100, dtype=tf.float32, name='C')
    y = tf.multiply(x, c, name='y')
    with tf.gfile.GFile("test_graph/y.pb", "wb") as f:
        raw = gf.as_graph_def().SerializeToString()
        f.write(raw)

加载回张量流图：

persisted_sess = tf.Session()
with persisted_sess.as_default():
    with gfile.FastGFile("./test_graph/y.pb",'rb') as f:
        graph_def = tf.GraphDef()
        graph_def.ParseFromString(f.read())
        persisted_sess.graph.as_default()
        tf.import_graph_def(graph_def, name='')
        for i, op in enumerate(persisted_sess.graph.get_operations()):
            tensor = persisted_sess.graph.get_tensor_by_name(op.name + ':0')
            print(i, '\t', op.name, op.type, tensor)
        x_tensor = persisted_sess.graph.get_tensor_by_name('x:0')
        y_tensor = persisted_sess.graph.get_tensor_by_name('y:0')

我们可以看到x 和y 操作和张量：

0    x Placeholder Tensor("x:0", shape=(?, 123), dtype=float32)
1    C Const Tensor("C:0", shape=(), dtype=float32)
2    y Mul Tensor("y:0", shape=(?, 123), dtype=float32)

然后我尝试使用不同的方法将其包装到 keras 模型中：

方法一：

output_layer = Lambda(lambda x: y_tensor, name='output_y')(x_tensor)
model = Model(inputs=[x_tensor], outputs=[output_layer])  # ERROR!

这已经产生错误InvalidArgumentError: You must feed a value for placeholder tensor 'x' with dtype float and shape [?,123] [[{{node x}}]]

方法二：

input_x = Input(name='x', shape=(123,), dtype='float32')
output_layer = Lambda(lambda x: y_tensor, name='output_y')(input_x)
model = Model(inputs=[input_x], outputs=[output_layer]) # OK

model.predict({'x': np.ones((3, 123), dtype=np.float32)}) # ERROR!

这会在predict 调用中导致同样的错误。

我能找到的与我的问题相关的最接近的信息是this，但它没有解决占位符的处理问题。这样做的正确方法是什么？

Answer 1

我找到了方法。我们需要使用InputLayer 而不是Input。

首先是创建演示张量流图 PB 的代码：

def dump_model(): # just to hide all vars during creation demo
    import numpy as np
    import sys
    import tensorflow as tf
    with tf.Graph().as_default() as gf:
        x = tf.placeholder(tf.float32, shape=(None, 123), name='x')
        b = tf.placeholder(tf.float32, shape=(None, 123), name='b')
        c = tf.constant(100, dtype=tf.float32, name='C')
        y = tf.multiply(x, c, name='y')
        z = tf.add(y, x, name='z')
        print(x, b, c, y, z)
        with tf.gfile.GFile("test_graph/y.pb", "wb") as f:
            raw = gf.as_graph_def().SerializeToString()
            print(type(raw), len(raw))
            f.write(raw)
dump_model()

然后导入图并找到输入/输出张量：

import numpy as np
import sys
import tensorflow as tf

persisted_sess = tf.Session()
with tf.Session().as_default() as session:
    with tf.gfile.FastGFile("./test_graph/y.pb",'rb') as f:
        graph_def = tf.GraphDef()
        graph_def.ParseFromString(f.read())
        persisted_sess.graph.as_default()
        tf.import_graph_def(graph_def, name='')
        print(persisted_sess.graph.get_name_scope())
        for i, op in enumerate(persisted_sess.graph.get_operations()):
            tensor = persisted_sess.graph.get_tensor_by_name(op.name + ':0')
            print(i, '\t', op.name, op.type, tensor)
        x_tensor = persisted_sess.graph.get_tensor_by_name('x:0')
        b_tensor = persisted_sess.graph.get_tensor_by_name('b:0')
        y_tensor = persisted_sess.graph.get_tensor_by_name('y:0')
        z_tensor = persisted_sess.graph.get_tensor_by_name('z:0')

然后我们可以创建keras模型并进行推理：

from tensorflow.keras.layers import Lambda, InputLayer
from tensorflow.keras import Model
from tensorflow.python.util import nest
from tensorflow.python.keras.utils import layer_utils

input_x = InputLayer(name='x', input_tensor=x_tensor)
input_x.is_placeholder = True  # this is the critical bits
input_b = InputLayer(name='b2', input_tensor=b_tensor) # note the keras name can be different than the tf name
input_b.is_placeholder = True
output_y = Lambda(lambda x: y_tensor, name='output_y')(input_x.output)
output_z = Lambda(lambda x_b: z_tensor, name='output_z')([input_x.output, input_b.output])

base_model_inputs = nest.flatten([layer_utils.get_source_inputs(input_x.output),
                                  layer_utils.get_source_inputs(input_b.output)])
base_model = Model(base_model_inputs, [output_y, output_z])
y_out, z_out = base_model.predict({'x': np.ones((3, 123), dtype=np.float32),
                                   'b2': np.full((3, 123), 100.0, dtype=np.float32)})
y_out.shape, z_out.shape

我们甚至可以从基础模型创建一个新模型：

from tensorflow.keras.layers import Add
derived_output = Add(name='derived')([output_y, output_z])
derived_model = Model(base_model.inputs, [derived_output])

derived_out = derived_model.predict({'x': np.ones((3, 123), dtype=np.float32),
                                                   'b2': np.full((3, 123), 100.0, dtype=np.float32)})
derived_out.shape