tf-distribution-options/code/train_hvd.py [17:56]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
logging.getLogger().setLevel(logging.INFO)
tf.logging.set_verbosity(tf.logging.ERROR)


#  Copy inference pre/post-processing script so it will be included in the model package
os.system('mkdir /opt/ml/model/code')
os.system('cp inference.py /opt/ml/model/code')
os.system('cp requirements.txt /opt/ml/model/code')


class CustomTensorBoardCallback(TensorBoard):
    
    def on_batch_end(self, batch, logs=None):
        pass

    
def save_history(path, history):

    history_for_json = {}
    # transform float values that aren't json-serializable
    for key in list(history.history.keys()):
        if type(history.history[key]) == np.ndarray:
            history_for_json[key] == history.history[key].tolist()
        elif type(history.history[key]) == list:
           if  type(history.history[key][0]) == np.float32 or type(history.history[key][0]) == np.float64:
               history_for_json[key] = list(map(float, history.history[key]))

    with codecs.open(path, 'w', encoding='utf-8') as f:
        json.dump(history_for_json, f, separators=(',', ':'), sort_keys=True, indent=4) 


def save_model(model, output):

    # create a TensorFlow SavedModel for deployment to a SageMaker endpoint with TensorFlow Serving
    tf.contrib.saved_model.save_keras_model(model, args.model_dir)
    logging.info("Model successfully saved at: {}".format(output))
    return


def main(args):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tf-distribution-options/code/train_ps.py [17:55]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
logging.getLogger().setLevel(logging.INFO)
tf.logging.set_verbosity(tf.logging.ERROR)


#  Copy inference pre/post-processing script so it will be included in the model package
os.system('mkdir /opt/ml/model/code')
os.system('cp inference.py /opt/ml/model/code')
os.system('cp requirements.txt /opt/ml/model/code')


class CustomTensorBoardCallback(TensorBoard):
    def on_batch_end(self, batch, logs=None):
        pass
    
    
def save_history(path, history):

    history_for_json = {}
    # transform float values that aren't json-serializable
    for key in list(history.history.keys()):
        if type(history.history[key]) == np.ndarray:
            history_for_json[key] == history.history[key].tolist()
        elif type(history.history[key]) == list:
           if  type(history.history[key][0]) == np.float32 or type(history.history[key][0]) == np.float64:
               history_for_json[key] = list(map(float, history.history[key]))

    with codecs.open(path, 'w', encoding='utf-8') as f:
        json.dump(history_for_json, f, separators=(',', ':'), sort_keys=True, indent=4) 


def save_model(model, output):

    # create a TensorFlow SavedModel for deployment to a SageMaker endpoint with TensorFlow Serving
    tf.contrib.saved_model.save_keras_model(model, args.model_dir)
    logging.info("Model successfully saved at: {}".format(output))
    return


def main(args):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -