Get the App
SLTechnology News&Howtos  ›  Internet Technology  › 

Interpretation of tensorflow serving catalogue

Shulou Source: shulou.com Published: 2022-06-03 07:40:28 10月02日 Update

Tf_serving-WORKSPACE

| |

-tensorflow-serving/----BUILD

| | |

| |-workspace.bzl |

| | |

| |-example/-BUILD |

| | |

| |-imagenet_lsvrc_2015_synsets.txt |

| | |

| |-imagenet_metadata.txt |

| | |

| |-inception_client.cc |

| | |

| |-inception_client.py |

| | |

| |-inception_k8s.yaml |

| | |

| |-inception_saved_model.py |

| | |

| |-mnist_client.py |

| | |

| |-mnist_iput_data.py |

| | |

| |-mnist_saved_model.py |

| |

-tensorflow/-BUILD

| | |

| |-WORKSPACE |

| | |

| |-tensorflow/-BUILD |

| | |

| |-workspace.bzl |

| |

-tf_models/----WORKSPACE

| |

-official/

| |

-tutorials/

| |

-research/-inception/-WORKSPACE

| |

-inception/-BUILD

| |

-inception_train.py

| |

-inception_model.py

| |

-inception_eval.py

| |

-inception_distributed_train.py

Interpretation:

The project folder name is "tf_serving" and the WORKSPACE file is placed in the root directory of the "tf_serving" project folder

*

Tf_serving/WORKSPACE interpretation:

*

# declare the workspace name, consistent with the project name workspace (name = "tf_serving") # declare the name and path local_repository of the local warehouse 'tensorflow' (name = "org_tensorflow", path = "tensorflow",) # declare io_bazel_rules_closurehttp_archive (…) # add a new Tensorflow Serving dependency to workspace.bzlload ("/ / tensorflow_serving:workspace.bzl", "tf_serving_workspace") tf_serving_workspace () # specify the bazel minimum required version load ("@ org_tensorflow//tensorflow::workspace.bzl", "check_version") check_version ("0.5.4")

*

Tf_serving/tensorflow_serving/workspace.bzl interpretation:

*

# tensorFlow Serving external dependencies are loaded into the WORKSPACE file load ('@ org_tensorflow//tensorflow::workspace.bzl', 'tf_workspace') # here are external dependencies for all Tensorflow Serving. # workspace_dir is the absolute path of Tensorflow Serving repo, if it is a submodule# connection The path form should be'_ workspace_dir__ + "serving" 'def tf_serving_workspace (): native.new_local_repository (name = "inception_model", path = "tf_models/research/inception", build_file = "tf_models/research/inception/inception/BUILD",) tf_workspace (path_prefix = "", tf_repo_name = "org_tensorflow") # gRPC depends on native.bind (name = "libssl") Actual = "@ boringssl//:ssl",) native.bind (name = "zlib", actual = "@ zlib_archive//:zlib")

*

Tf_serving/tensorflow_serving/BUILD interpretation:

*

# Tensorflow serving describes package (default_visibility= ["/ tensorflow_serving:internal"],) licenses (["notice"]) exports_files (["LICENSE"]) # Open Source tag package_group (name = "internal", package = ["/ / tensorflow_serving/...",],) filegroup (name = "all_files", srcs = glob (["* * /"], exclude = ["* * / METADATA", "* * / OWNERS", "g3doc/sitemap.md",],),)

*

Tf_serving/tensorflow/tensorflow/workspace.bzl interpretation:

*

# Tensorflow externally dependent load (...) that can be loaded in a WORKSPACE file Def _ is_windows ():... Def _ get_env_var ():... # parsing the bazel version string def _ parse_bazel_version (): from 'native.bazel_version' # check that you are using the specified version of bazeldef check_version ():... # support Tensorflow as the temporary workspace of submodule def _ temp_workaround_http_archive_impl ():... # if you exit with non-zero code, execute the command that specifies the parameter and call 'fail'def _ execute_and_check_ret_code ():... # apply the patch file def _ apply_patch (): … in the root directory of the repository # download the repository, and apply the patch def _ patched_http_archive_impl (): … in the root node # if the Tensorflow connection is submodule,path_prefix and is no longer used # tf_repo_name is considering def tf_workspace (): …

*

Tf_serving/tensorflow/tensorflow/BUILD interpretation:

*

Package (default_visibility = [": internal"]) licenses (["notice"]) exports_files (["LICENSE", "ACKNOWLEDGMENTS", # leakr file for / / third_party/cloud_tpu "leakr_badwords.dic", "leakr_badfiles.dic",]) load ("/ / tensorflow:tensorflow.bzl", "tf_cc_shared_object") load ("/ / tensorflow/core:platform/default/build_config.bzl", "tf_additional_binary_deps") ) # various config settingconfig_setting () package_group () filegroup () py_library () filegroup (name = "all_opensource_files", data = [": all_files", "/ / tensorflow/c:all_files", "/ / tensorflow/cc:all_files",.] , visibility = [': _ _ subpackages__'],) load ("/ / third_party/mkl:build_defs.bzl", "if_mkl",) filegroup (name = "intel_binary_blob", data = if_mkl (["/ / third_party/mkl:intel_binary_blob",],),) filegroup (name = "docs_src", data = glob (["docs_src/**/*.md"]),) tf_cc_shared_object (.)

Tags: File name repository version path project folder root directory in progress patch work application minimum consistent parameter command character string workspace form Apple Docker Huawei Linux macOS MariaDB Microsoft MySQL NVidia OPPO Reno Xiaomi MySQL Apple Huawei NVidia