Tensorflow 2中使用保存模型的推理:如何在/输出中控制？
Tensorflow 2中使用保存模型的推理:如何在/输出中控制？
提问于 2022-01-11 01:04:50
将我的代码从TF1调整到TF2.6，我遇到了麻烦。我试图添加一些自定义层到一个初始resnet，保存模型，然后加载和运行它。
from tensorflow.keras.layers import Dense
from tensorflow.keras.models import Model
from tensorflow.keras.applications.inception_resnet_v2 import InceptionResNetV2
from tensorflow.keras.layers import Dense, GlobalAveragePooling2D
import tensorflow as tf
import numpy as np
from PIL import Image
export_path = "./save_test"
# Get model without top and add two layers
base_model = InceptionResNetV2(weights='imagenet', input_tensor=None, include_top=False)
out = base_model.output
out = GlobalAveragePooling2D()(out)
predictions = Dense(7, activation='softmax', name="output")(out)
# Make new model using inputs from base model and custom outputs
model = Model(inputs=base_model.input, outputs=[predictions])
# save model
tf.saved_model.save(model, export_path)
# load model and run
with tf.compat.v1.Session(graph=tf.Graph()) as sess:
tf.compat.v1.saved_model.loader.load(sess, ['serve'], export_path)
graph = tf.compat.v1.get_default_graph()
img = Image.new('RGB', (299, 299))
x = tf.keras.preprocessing.image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = x[..., :3]
x /= 255.0
x = (x - 0.5) * 2.0
y_pred = sess.run('output/Softmax:0', feed_dict={'serving_default_input_1:0': x}) 错误：KeyError: "The name 'output/Softmax:0' refers to a Tensor which does not exist. The operation, 'output/Softmax', does not exist in the graph."
我不明白的是：predictions.name是'output/Softmax:0'，但是graph.get_tensor_by_name('output/Softmax:0')告诉我它不存在！
注意：我知道我可以用TF2的tf.keras.models.save和tf.keras.models.load_model保存和加载模型，然后用model(x)运行模型。但是，在我的应用程序中，我在内存中有多个模型，并且我发现推理所用的时间比使用TF1对象的session代码要长得多。因此，我希望在兼容模式下对TF1对象使用session方法。
如何在保存时控制输入/输出的名称？我遗漏了什么？
回答 1
Stack Overflow用户
发布于 2022-01-14 17:49:20
在TF2.0、2.6和2.7上测试
如果您还没有这样做，您可以尝试如下所示，因为我认为您在SignatureDef中引用了错误的键
from tensorflow.keras.layers import Dense
from tensorflow.keras.models import Model
from tensorflow.keras.applications.inception_resnet_v2 import InceptionResNetV2
from tensorflow.keras.layers import Dense, GlobalAveragePooling2D
import tensorflow as tf
import numpy as np
from PIL import Image
export_path = "./save_test"
base_model = InceptionResNetV2(weights='imagenet', input_tensor=None, include_top=False)
out = base_model.output
out = GlobalAveragePooling2D()(out)
predictions = Dense(7, activation='softmax', name="output")(out)
model = Model(inputs=base_model.input, outputs=[predictions])
tf.saved_model.save(model, export_path)
with tf.compat.v1.Session(graph=tf.Graph()) as sess:
meta_graph = tf.compat.v1.saved_model.loader.load(sess, ["serve"], export_path)
sig_def = meta_graph.signature_def[tf.saved_model.DEFAULT_SERVING_SIGNATURE_DEF_KEY]
input_key = list(dict(sig_def.inputs).keys())[0]
input_name = sig_def.inputs[input_key].name
output_name = sig_def.outputs['output'].name
img = Image.new('RGB', (299, 299))
x = tf.keras.preprocessing.image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = x[..., :3]
x /= 255.0
x = (x - 0.5) * 2.0
y_pred = sess.run(output_name, feed_dict={input_name: x})
print(y_pred) INFO:tensorflow:Restoring parameters from ./save_test/variables/variables
[[0.14001141 0.13356228 0.14509581 0.22432518 0.16313255 0.11899492
0.07487784]]您还可以查看输入和输出信息的SignatureDef：
print(meta_graph.signature_def)
{'serving_default': inputs {
key: "input_2"
value {
name: "serving_default_input_2:0"
dtype: DT_FLOAT
tensor_shape {
dim {
size: -1
}
dim {
size: -1
}
dim {
size: -1
}
dim {
size: 3
}
}
}
}
outputs {
key: "output"
value {
name: "StatefulPartitionedCall:0"
dtype: DT_FLOAT
tensor_shape {
dim {
size: -1
}
dim {
size: 7
}
}
}
}
method_name: "tensorflow/serving/predict"
, '__saved_model_init_op': outputs {
key: "__saved_model_init_op"
value {
name: "NoOp"
tensor_shape {
unknown_rank: true
}
}
}
}如果删除base_model的第一层并添加新的Input层，则可以使用静态键名sig_def.inputs['input'].name和sig_def.outputs['output'].name。
from tensorflow.keras.layers import Dense
from tensorflow.keras.models import Model
from tensorflow.keras.applications.inception_resnet_v2 import InceptionResNetV2
from tensorflow.keras.layers import Dense, GlobalAveragePooling2D
import tensorflow as tf
import numpy as np
from PIL import Image
export_path = "./save_test"
base_model = InceptionResNetV2(weights='imagenet', input_tensor=None, include_top=False)
base_model.layers.pop(0)
new_input = tf.keras.layers.Input(shape=(299,299,3), name='input')
out = base_model(new_input)
out = GlobalAveragePooling2D()(out)
predictions = Dense(7, activation='softmax', name="output")(out)
model = Model(inputs=new_input, outputs=[predictions])
tf.saved_model.save(model, export_path)
with tf.compat.v1.Session(graph=tf.Graph()) as sess:
meta_graph = tf.compat.v1.saved_model.loader.load(sess, ["serve"], export_path)
sig_def = meta_graph.signature_def[tf.saved_model.DEFAULT_SERVING_SIGNATURE_DEF_KEY]
input_name = sig_def.inputs['input'].name
output_name = sig_def.outputs['output'].name
img = Image.new('RGB', (299, 299))
x = tf.keras.preprocessing.image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = x[..., :3]
x /= 255.0
x = (x - 0.5) * 2.0
y_pred = sess.run(output_name, feed_dict={input_name: x})
print(y_pred) INFO:tensorflow:Restoring parameters from ./save_test/variables/variables
[[0.21079363 0.10773096 0.07287834 0.06983061 0.10538215 0.09172108
0.34166315]]注意，更改base_model第一层的名称不适用于语法model.layers[0]._name = 'input'，因为模型配置本身不会被更新。
页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/70660544
复制相关文章
相似问题
腾讯云开发者
