3

I use ssd_mobilenets in Object detection API to train my own model, and get .ckpt files. It works well on my computer, but now I want to use the model on my phone. So, I need convert it to .pb file. I do not know how to do it, can any one help? By the way, the graph of ssd_mobilenets is complex, I can not find which is the output of model. Is there any one knowing the name of the output?

Seven.L
  • 93
  • 2
  • 8

2 Answers2

2

Use export_inference_graph.py to convert model checkpoint file into a .pb file.

python tensorflow_models/object_detection/export_inference_graph.py \
--input_type image_tensor \
--pipeline_config_path architecture_used_while_training.config \
--trained path_to_saved_ckpt/model.ckpt-NUMBER \
--output_directory model/
Salman Ghauri
  • 574
  • 1
  • 5
  • 16
  • I created a `.ckpt` file using `tf.train.Saver()`, but it didn't give me a `.config` file. Where does that come from? – jss367 Aug 14 '19 at 14:55
  • Use the same config file that you used to train the model or take one from sample configs given by TF – Salman Ghauri Aug 15 '19 at 07:52
0

  • This is the 4th code cell in object_detection_tutorial.ipynb in this link -https://github.com/tensorflow/models/blob/master/research/object_detection/object_detection_tutorial.ipynb

    # What model to download.
MODEL_NAME = 'ssd_mobilenet_v1_coco_2017_11_17'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'

# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'

# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')

NUM_CLASSES = 90

  • Now the cell clearly says the .pb filename which is /frozen_inference_graph.pb

  • So you already have the .pb file why do you want to convert ??
  • Anyways you can refer thsi link for freezing the graph: https://github.com/jayshah19949596/Tensorboard-Visualization-Freezing-Graph
  • you need to use tensorflow.python.tools.freeze_graph() function to convert your .ckpt file to .pb file

  • The below code line shows how you do it 

    freeze_graph.freeze_graph(input_graph_path,
                          input_saver_def_path,
                          input_binary,
                          input_checkpoint_path,
                          output_node_names,
                          restore_op_name,
                          filename_tensor_name,
                          output_graph_path,
                          clear_devices,
                          initializer_nodes)
    • input_graph_path : is the path to .pb file where you will write your graph and this .pb file is not frozen. you will use tf.train.write_graph() to write the graph
    • input_saver_def_path : you can keep it an empty string
    • input_binary : it is a boolean value keep it false so that the file genertaed is not binary and human readable
    • input_checkpoint_path : path to the .ckpt file
    • output_graph_path : path where you want to write you pb file
    • clear_devices : boolean value ... keep it False
    • output_node_names : explicit tensor node names that you want to save
    • restore_op_name : string value that should be "save/restore_all"
    • filename_tensor_name = "save/Const:0"
    • initializer_nodes = ""
Jai
  • 3,211
  • 2
  • 17
  • 26
  • 1
    I don't understand `freeze_graph`. You're saying it converts a `.ckpt` file to a `.pb` file, but `input_graph_path` is a path to a pre-existing `.pb` file? Where does that come from? – jss367 Aug 14 '19 at 14:57