如何在 TF2 的 Keras Lambda 层中包装冻结的 Tensorflow 图？

Question

此问题与 this question 有关，它提供了在 Tensorflow 1.15 中有效的解决方案，但在 TF2

中不再有效

我正在从那个问题中提取部分代码并稍微调整它（删除了冻结模型的多个输入，并随之删除了对 nest 的需求）。

注意：我将代码分成块，但它们应该是文件中的运行（即，我不会重复每个块中不必要的导入）

首先，我们生成一个冻结图用作虚拟测试网络：

import numpy as np
import tensorflow.compat.v1 as tf

def dump_model():
    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')
        z = tf.add(y, x, name='z')
        with tf.gfile.GFile("tmp_net.pb", "wb") as f:
            raw = gf.as_graph_def().SerializeToString()
            print(type(raw), len(raw))
            f.write(raw)

dump_model()

然后，我们加载冻结模型并将其包装在 Keras 模型中：

persisted_sess = tf.Session()
with tf.Session().as_default() as session:
    with tf.gfile.FastGFile("./tmp_net.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')
        y_tensor = persisted_sess.graph.get_tensor_by_name('y:0')
        z_tensor = persisted_sess.graph.get_tensor_by_name('z:0')

from tensorflow.compat.v1.keras.layers import Lambda, InputLayer
from tensorflow.compat.v1.keras import Model
from tensorflow.python.keras.utils import layer_utils

input_x = InputLayer(name='x', input_tensor=x_tensor)
input_x.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)

base_model_inputs = layer_utils.get_source_inputs(input_x.output)
base_model = Model(base_model_inputs, [output_y, output_z])

最后，我们运行一些随机数据的模型并验证它运行没有错误：

y_out, z_out = base_model.predict(np.ones((3, 123), dtype=np.float32))
y_out.shape, z_out.shape

在Tensorflow 1.15.3中，上面的输出是((3, 123), (3, 123))，但是，如果我在Tensorflow 2.1.0中运行相同的代码，前两个块运行没有问题，但是第三个失败了：

TypeError: An op outside of the function building code is being passed
a "Graph" tensor. It is possible to have Graph tensors
leak out of the function building context by including a
tf.init_scope in your function building code.
For example, the following function will fail:
  @tf.function
  def has_init_scope():
    my_constant = tf.constant(1.)
    with tf.init_scope():
      added = my_constant * 2
The graph tensor has name: y:0

错误似乎与Tensorflow的自动“编译”和功能优化有关，但我不知道如何解释，错误来源是什么，或者如何解决。

在 Tensorflow 2 中包裹冻结模型的正确方法是什么？

Answer 1

我可以运行你的整个例子在 2.2.0 中是这样的。

import tensorflow as tf
from tensorflow.core.framework.graph_pb2 import GraphDef
import numpy as np

with tf.Graph().as_default() as gf:
    x = tf.compat.v1.placeholder(tf.float32, shape=(None, 123), name='x')
    c = tf.constant(100, dtype=tf.float32, name='c')
    y = tf.multiply(x, c, name='y')
    z = tf.add(y, x, name='z')
    with open('tmp_net.pb', 'wb') as f:
        f.write(gf.as_graph_def().SerializeToString())

with tf.Graph().as_default():
    gd = GraphDef()
    with open('tmp_net.pb', 'rb') as f:
        gd.ParseFromString(f.read())
    x, y, z = tf.graph_util.import_graph_def(
        gd, name='', return_elements=['x:0', 'y:0', 'z:0'])
    del gd
    input_x = tf.keras.layers.InputLayer(name='x', input_tensor=x)
    input_x.is_placeholder = True
    output_y = tf.keras.layers.Lambda(lambda x: y, name='output_y')(input_x.output)
    output_z = tf.keras.layers.Lambda(lambda x: z, name='output_z')(input_x.output)

    base_model_inputs = tf.keras.utils.get_source_inputs(input_x.output)
    base_model = tf.keras.Model(base_model_inputs, [output_y, output_z])

    y_out, z_out = base_model.predict(np.ones((3, 123), dtype=np.float32))
    print(y_out.shape, z_out.shape)
    # (3, 123) (3, 123)

“诀窍”是将模型构建包装在一个 with tf.Graph().as_default(): 块中，这将确保所有内容都在同一个图形对象中以图形模式创建。

但是，将图形加载和计算封装在一个@tf.function中可能会更简单，这样可以避免此类错误并使模型构建更加透明：

import tensorflow as tf
from tensorflow.core.framework.graph_pb2 import GraphDef
import numpy as np

@tf.function
def my_model(x):
    gd = GraphDef()
    with open('tmp_net.pb', 'rb') as f:
        gd.ParseFromString(f.read())
    y, z = tf.graph_util.import_graph_def(
        gd, name='', input_map={'x:0': x}, return_elements=['y:0', 'z:0'])
    return [y, z]

x = tf.keras.Input(shape=123)
y, z = tf.keras.layers.Lambda(my_model)(x)
model = tf.keras.Model(x, [y, z])
y_out, z_out = model.predict(np.ones((3, 123), dtype=np.float32))
print(y_out.shape, z_out.shape)
# (3, 123) (3, 123)

Answer 2

另一种可能的方法是

import tensorflow as tf

input_layer = tf.keras.Input(shape=[123])
keras_graph = input_layer.graph

with keras_graph.as_default():
    with tf.io.gfile.GFile('tmp_net.pb', 'rb') as f:
        graph_def = tf.compat.v1.GraphDef()
        graph_def.ParseFromString(f.read())

    tf.graph_util.import_graph_def(graph_def, name='', input_map={'x:0': input_layer})
    
    
y_tensor = keras_graph.get_tensor_by_name('y:0')
z_tensor = keras_graph.get_tensor_by_name('z:0')

base_model = tf.keras.Model(input_layer, [y_tensor, z_tensor])

然后

y_out, z_out = base_model.predict(tf.ones((3, 123), dtype=tf.float32))
print(y_out.shape, z_out.shape)
# (3, 123) (3, 123)

如何在 TF2 的 Keras Lambda 层中包装冻结的 Tensorflow 图？

How to wrap a frozen Tensoflow graph in a Keras Lambda layer in TF2?

python

keras

tensorflow

tensorflow2.0