cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
kronos_kairos
Visitor
Visitor
225 Views
Registered: ‎04-19-2021

vai_q_tensorflow rebuild error

Jump to solution

I tried the rebuild vai_q_tensorflow.
https://github.com/Xilinx/Vitis-AI/tree/v1.3/tools/Vitis-AI-Quantizer/vai_q_tensorflow1.x

However following error occurred.

~/Vitis-AI/tools/Vitis-AI-Quantizer/vai_q_tensorflow1.x$ sh rebuild_cpu.sh
INFO: Options provided by the client:
Inherited 'common' options: --isatty=1 --terminal_columns=84
INFO: Reading rc options for 'build' from ~/Vitis-AI/tools/Vitis-AI-Quantizer/vai_q_tensorflow1.x/.bazelrc:
'build' options: --apple_platform_type=macos --define framework_shared_object=true --define open_source_build=true --define=use_fast_cpp_protos=true --define=allow_oversize_protos=true --spawn_strategy=standalone -c opt --announce_rc --define=grpc_no_ares=true --define=PREFIX=/usr --define=LIBDIR=$(PREFIX)/lib --define=INCLUDEDIR=$(PREFIX)/include --copt=-w --config=v1
INFO: Reading rc options for 'build' from ~/Vitis-AI/tools/Vitis-AI-Quantizer/vai_q_tensorflow1.x/.tf_configure.bazelrc:
'build' options: --host_force_python=PY2 --action_env PYTHON_BIN_PATH=/usr/bin/python --action_env PYTHON_LIB_PATH=/usr/local/lib/python2.7/dist-packages --python_path=/usr/bin/python --config=xla --action_env TF_CONFIGURE_IOS=0
INFO: Found applicable config definition build:v1 in file ~/Vitis-AI/tools/Vitis-AI-Quantizer/vai_q_tensorflow1.x/.bazelrc: --define=tf_api_version=1 --action_env=TF2_BEHAVIOR=0
INFO: Found applicable config definition build:xla in file ~/Vitis-AI/tools/Vitis-AI-Quantizer/vai_q_tensorflow1.x/.bazelrc: --action_env=TF_ENABLE_XLA=1 --define=with_xla_support=true
INFO: Found applicable config definition build:xla in file ~/Vitis-AI/tools/Vitis-AI-Quantizer/vai_q_tensorflow1.x/.tf_configure.bazelrc: --define with_xla_support=true
INFO: Found applicable config definition build:opt in file ~/Vitis-AI/tools/Vitis-AI-Quantizer/vai_q_tensorflow1.x/.tf_configure.bazelrc: --copt=-march=native --copt=-Wno-sign-compare --host_copt=-march=native --define with_default_optimizations=true
ERROR: ~/Vitis-AI/tools/Vitis-AI-Quantizer/vai_q_tensorflow1.x/tensorflow/tools/pip_package/BUILD:232:1: no such package 'tensorflow/lite/python/testdata': BUILD file not found on package path and referenced by '//tensorflow/tools/pip_package:build_pip_package'
ERROR: Analysis of target '//tensorflow/tools/pip_package:build_pip_package' failed; build aborted: no such package 'tensorflow/lite/python/testdata': BUILD file not found on package path
INFO: Elapsed time: 0.065s
INFO: 0 processes.
FAILED: Build did NOT complete successfully (0 packages loaded, 0 targets configur\
ed)

I guress that 'tensorflow/lite/python/testdata/BUILD' is not found.
Is there any operation I should do ?

0 Kudos
1 Solution

Accepted Solutions
xieyi
Xilinx Employee
Xilinx Employee
102 Views
Registered: ‎03-23-2021

Hi @kronos_kairos , Thank you for your feedback.

I have fixed this bug and create a new pull request.  https://github.com/Xilinx/Vitis-AI/pull/400

Before the pull request being accepted, you can clone the repo folked by me.  https://github.com/xieyi4650/Vitis-AI/tree/1.3.2

files are added to branch 1.3.2

View solution in original post

0 Kudos
3 Replies
linqiang
Xilinx Employee
Xilinx Employee
117 Views
Registered: ‎05-10-2019

Hi @kronos_kairos 

Thank you for your feedback.

It's a bug for vai_q_tensorflow on macos. We will fix it in VAI1.4.

0 Kudos
xieyi
Xilinx Employee
Xilinx Employee
103 Views
Registered: ‎03-23-2021

Hi @kronos_kairos , Thank you for your feedback.

I have fixed this bug and create a new pull request.  https://github.com/Xilinx/Vitis-AI/pull/400

Before the pull request being accepted, you can clone the repo folked by me.  https://github.com/xieyi4650/Vitis-AI/tree/1.3.2

files are added to branch 1.3.2

View solution in original post

0 Kudos
kronos_kairos
Visitor
Visitor
68 Views
Registered: ‎04-19-2021

Hi @xieyi , @linqiang 

Thank you for your support.

I used forked branch, vai_q_tensorflow build and execute successfully !

best regards.

0 Kudos