search

googlecodelabs / tensorflow-for-poets-2

Apache License 2.0
507 stars 465 forks source link

Missing requirement for installing TensorFlow version. #123

Open rrifafauzikomara opened 5 years ago

rrifafauzikomara commented 5 years ago

I learn tensorflow from: https://codelabs.developers.google.com/codelabs/tensorflow-for-poets-2-tflite/#0

In step 2, we install tensorflow version 1.7, but in step 3 we want to run "tflite_convert" so in tensorflow 1.7 it's not available and you must install tensorflow version to 1.9 for run "tensorflow version". More info: https://www.tensorflow.org/lite/convert/cmdline_examples

Thanks :+1:

rrifafauzikomara commented 5 years ago

but, if I want run tflite_convert in step 3 sub Convert to model to TFLite format,

IMAGE_SIZE=224
tflite_convert \
  --graph_def_file=tf_files/retrained_graph.pb \
  --output_file=tf_files/optimized_graph.lite \
  --input_format=TENSORFLOW_GRAPHDEF \
  --output_format=TFLITE \
  --input_shape=1,${IMAGE_SIZE},${IMAGE_SIZE},3 \
  --input_array=input \
  --output_array=final_result \
  --inference_type=FLOAT \
  --input_data_type=FLOAT

I get the error tflite_convert: error: like this:

usage: tflite_convert [-h] --output_file OUTPUT_FILE
                      (--graph_def_file GRAPH_DEF_FILE | --saved_model_dir SAVED_MODEL_DIR)
                      [--output_format {TFLITE,GRAPHVIZ_DOT}]
                      [--inference_type {FLOAT,QUANTIZED_UINT8}]
                      [--inference_input_type {FLOAT,QUANTIZED_UINT8}]
                      [--input_arrays INPUT_ARRAYS]
                      [--input_shapes INPUT_SHAPES]
                      [--output_arrays OUTPUT_ARRAYS]
                      [--saved_model_tag_set SAVED_MODEL_TAG_SET]
                      [--saved_model_signature_key SAVED_MODEL_SIGNATURE_KEY]
                      [--std_dev_values STD_DEV_VALUES]
                      [--mean_values MEAN_VALUES]
                      [--default_ranges_min DEFAULT_RANGES_MIN]
                      [--default_ranges_max DEFAULT_RANGES_MAX]
                      [--drop_control_dependency DROP_CONTROL_DEPENDENCY]
                      [--reorder_across_fake_quant REORDER_ACROSS_FAKE_QUANT]
                      [--change_concat_input_ranges CHANGE_CONCAT_INPUT_RANGES]
                      [--allow_custom_ops ALLOW_CUSTOM_OPS]
tflite_convert: error:

Anyone can help me ?