ImportError：没有名为“ tensorflow.contrib.lite.python.tflite_convert”的模块

Question

I tried tflite_convert to convert my saved_model.pb(object detection API) file to .tflite but when i execute this command on cmd on the directory of C:\\Users\\LENOVO-PC\\tensorflow> where tensorflow git is cloned,

tflite_convert \ --output_file=/saved_model/maonani.tflite \ --saved_model_dir=/saved_model/saved_model

I get an error saying

ImportError: No module named 'tensorflow.contrib.lite.python.tflite_convert'

the complete sourcelog is

C:\Users\LENOVO-PC\tensorflow>tflite_convert \ --output_file=/saved_model/maonani.tflite \ --saved_model_dir=/saved_model/saved_model
Traceback (most recent call last):
  File "c:\users\lenovo-pc\appdata\local\programs\python\python35\lib\runpy.py", line 184, in _run_module_as_main
    "__main__", mod_spec)
  File "c:\users\lenovo-pc\appdata\local\programs\python\python35\lib\runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "C:\Users\LENOVO-PC\AppData\Local\Programs\Python\Python35\Scripts\tflite_convert.exe\__main__.py", line 5, in <module>
ImportError: No module named 'tensorflow.contrib.lite.python.tflite_convert'

is there anyway to convert my .pb file to .tflite on WINDOWS?

Answer 1

Hi my solution was using linux in the following way Windows Subsystem for Linux - see

then install from store ubunto

then need to pip3 install --upgrade "tensorflow=1.7*" then if you try to run toco it would not be recognized.

the solution is go to folder

~/.local/bin/

there you would find toco, this is a python file.

run

python3 ~/.local/bin/toco

you would get the "exe" of toco.

to convert you can run the command explained in https://codelabs.developers.google.com/codelabs/tensorflow-for-poets-2-tflite/#2

just change the -graph_def_file=tf_files/retrained_graph.pb to --input_file=tf_files/retrained_graph.pb

Hope this helps someone

Note: if you are missing pip3, you would need to install it

Answer 2

I follow the instruction on this site:

https://codelabs.developers.google.com/codelabs/tensorflow-for-poets-2-tflite/#2

However, it seems that tflearn_convert doesn't support Windows anymore. So i decided to use Ubuntu on Windows. After having created a virtual environment to install tensorflow, i checked "toco" by typing toco in the terminal. And there go the instruction to use toco.

usage: /home/hieu/venv/bin/toco

Flags:

    --input_file=""                         string  Input file (model of any supported format). For Protobuf formats, both text and binary are supported regardless of file extension.
    --output_file=""                        string  Output file. For Protobuf formats, the binary format will be used.
    --input_format=""                       string  Input file format. One of: TENSORFLOW_GRAPHDEF, TFLITE.
    --output_format=""                      string  Output file format. One of TENSORFLOW_GRAPHDEF, TFLITE, GRAPHVIZ_DOT.
    --default_ranges_min=0.000000           float   If defined, will be used as the default value for the min bound of min/max ranges used for quantization.
    --default_ranges_max=0.000000           float   If defined, will be used as the default value for the max bound of min/max ranges used for quantization.
    --inference_type=""                     string  Target data type of arrays in the output file (for input_arrays, this may be overridden by inference_input_type). One of FLOAT, QUANTIZED_UINT8.
    --inference_input_type=""               string  Target data type of input arrays. If not specified, inference_type is used. One of FLOAT, QUANTIZED_UINT8.
    --input_type=""                         string  Deprecated ambiguous flag that set both --input_data_types and --inference_input_type.
    --input_types=""                        string  Deprecated ambiguous flag that set both --input_data_types and --inference_input_type. Was meant to be a comma-separated list, but this was deprecated before multiple-input-types was ever properly supported.
    --drop_fake_quant=false                 bool    Ignore and discard FakeQuant nodes. For instance, to generate plain float code without fake-quantization from a quantized graph.
    --reorder_across_fake_quant=false       bool    Normally, FakeQuant nodes must be strict boundaries for graph transformations, in order to ensure that quantized inference has the exact same arithmetic behavior as quantized training --- which is the whole point of quantized training and of FakeQuant nodes in the first place. However, that entails subtle requirements on where exactly FakeQuant nodes must be placed in the graph. Some quantized graphs have FakeQuant nodes at unexpected locations, that prevent graph transformations that are necessary in order to generate inference code for these graphs. Such graphs should be fixed, but as a temporary work-around, setting this reorder_across_fake_quant flag allows TOCO to perform necessary graph transformaitons on them, at the cost of no longer faithfully matching inference and training arithmetic.
    --allow_custom_ops=false                bool    If true, allow TOCO to create TF Lite Custom operators for all the unsupported TensorFlow ops.
    --drop_control_dependency=false         bool    If true, ignore control dependency requirements in input TensorFlow GraphDef. Otherwise an error will be raised upon control dependency inputs.
    --debug_disable_recurrent_cell_fusion=false     bool    If true, disable fusion of known identifiable cell subgraphs into cells. This includes, for example, specific forms of LSTM cell.

And many more...

After that, i used this command to convert file:

 toco --input_file="tf_files/retrained_graph.pb" --output_file="tf_files/optimized_graph.lite" --input_format="TENSORFLOW_GRAPHDEF" --output_format="TFLITE" --input_shape="1,224,224,3" --input_array="input" --output_array="final_result" --inference_type="FLOAT" --input_data_type="FLOAT"

Then optimized_graph.lite should be found in tf_files

Answer 3

According to this thread : Tensorflow discussions

The issue really is that the module as of now is not supported on windows. You can follow the thread and see if there is an update regarding the same.

PS: some people claim that a git-clone and bazel build helped resloved the issue, instead of pip install, you can try that as well but have serious doubts if that will work.