67 lines (54 sloc) 2.12 KB

Running Locally

This page walks through the steps required to train an object detection model on a local machine. It assumes the reader has completed the following prerequisites:

  1. The Tensorflow Object Detection API has been installed as documented in the installation instructions. This includes installing library dependencies, compiling the configuration protobufs and setting up the Python environment.
  2. A valid data set has been created. See this page for instructions on how to generate a dataset for the PASCAL VOC challenge or the Oxford-IIIT Pet dataset.
  3. A Object Detection pipeline configuration has been written. See this page for details on how to write a pipeline configuration.

Recommended Directory Structure for Training and Evaluation

  -label_map file
  -train TFRecord file
  -eval TFRecord file
  + model
    -pipeline config file

Running the Training Job

A local training job can be run with the following command:

# From the tensorflow/models/research/ directory
PIPELINE_CONFIG_PATH={path to pipeline config file}
MODEL_DIR={path to model directory}
python object_detection/ \
    --pipeline_config_path=${PIPELINE_CONFIG_PATH} \
    --model_dir=${MODEL_DIR} \
    --num_train_steps=${NUM_TRAIN_STEPS} \
    --sample_1_of_n_eval_examples=$SAMPLE_1_OF_N_EVAL_EXAMPLES \

where ${PIPELINE_CONFIG_PATH} points to the pipeline config and ${MODEL_DIR} points to the directory in which training checkpoints and events will be written to. Note that this binary will interleave both training and evaluation.

Running Tensorboard

Progress for training and eval jobs can be inspected using Tensorboard. If using the recommended directory structure, Tensorboard can be run using the following command:

tensorboard --logdir=${MODEL_DIR}

where ${MODEL_DIR} points to the directory that contains the train and eval directories. Please note it may take Tensorboard a couple minutes to populate with data.