小编hec*_*rga的帖子

我使用inception_v3 跟随Codelab TensorFlow For Poets进行传输学习.它会生成retrained_graph.pb和retrained_labels.txt文件,这些文件可用于在本地进行预测(运行label_image.py).

然后,我想将此模型部署到Cloud ML Engine,以便我可以进行在线预测.为此,我必须将retrained_graph.pb导出为SavedModel格式.我设法通过遵循指示去做,从谷歌的@ rhaertel80这个答案和这条巨蟒文件从花云ML引擎教程.这是我的代码:

import tensorflow as tf
from tensorflow.contrib import layers

from tensorflow.python.saved_model import builder as saved_model_builder
from tensorflow.python.saved_model import signature_constants
from tensorflow.python.saved_model import signature_def_utils
from tensorflow.python.saved_model import tag_constants
from tensorflow.python.saved_model import utils as saved_model_utils


export_dir = '../tf_files/saved7'
retrained_graph = '../tf_files/retrained_graph2.pb'
label_count = 5

def build_signature(inputs, outputs):
    signature_inputs = { key: saved_model_utils.build_tensor_info(tensor) for key, tensor in inputs.items() }
    signature_outputs = { key: saved_model_utils.build_tensor_info(tensor) for key, …