how to convert .ckpt file to .pb

Question

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?

Answer 1

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/

Answer 2

• 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 = ""