尝试将我的keras模型导出到tensorflow服务时出错

Question

from tensorflow.python.saved_model import builder as saved_model_builder
export_path=r'tensorflowservingmodel'
export_version=1
builder = saved_model_builder.SavedModelBuilder(export_path)
signature = predict_signature_def(
    inputs={'input': new_model.inputs[0]},
    outputs={'output': new_model.outputs[0]})


with K.get_session() as sess:

    builder.add_meta_graph_and_variables(
        sess=sess,
        tags=[tag_constants.SERVING],
        clear_devices = True,
        signature_def_map={
            signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY: signature}
    )
builder.save()
print("tensorflow serving.......")

AssertionError Traceback（最近调用last）2 export_path = r'tensorflowservingmodel'3 export_version = 1 ----> 4 builder = saved_model_builder.SavedModelBuilder（export_path）5 signature = predict_signature_def（6 inputs = {'input'：new_model.inputs [0]}，〜\ anaconda \ lib \ site-packages \ tensorflow \ python \ saved_model \ builder_impl.py in init（self，export_dir）93引发AssertionError（94“导出目录已存在。请指定不同的导出” - - > 95“目录：％s”％export_dir）96 97 file_io.recursive_create_dir（self._export_dir）AssertionError：导出目录已存在。请指定不同的导出目录：tensorflowservingmodel

Answer 1

删除此目录'tensorflowservingmodel'，确保在导出模型之前它不存在。

rm -r tensorflowservingmodel

Answer 2

我发现问题已经创建了一个名为tensorflowservingmodel的文件，这就是为什么程序说目录已经存在.l必须删除文件目录并重新运行代码。