models之object_detection

model/research/object_detection/samples/configs

ssd_mobilenet_v1_quantized_300x300_coco14_sync.config

带quantized的模型，是不可以进行 fine_tune_checkpoint 操作，

报错

Traceback (most recent call last):

  File "train.py", line 184, in <module>

    tf.app.run()

  File "D:\Anaconda3\envs\tensorflow-gpu\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run

    _sys.exit(main(argv))

  File "D:\Anaconda3\envs\tensorflow-gpu\lib\site-packages\tensorflow\python\util\deprecation.py", line 272, in new_func

    return func(*args, **kwargs)

  File "train.py", line 180, in main

    graph_hook_fn=graph_rewriter_fn)

  File "D:\models-master\research\object_detection\legacy\trainer.py", line 397, in train

    init_saver = tf.train.Saver(available_var_map)

  File "D:\Anaconda3\envs\tensorflow-gpu\lib\site-packages\tensorflow\python\training\saver.py", line 1281, in __init__

    self.build()

  File "D:\Anaconda3\envs\tensorflow-gpu\lib\site-packages\tensorflow\python\training\saver.py", line 1293, in build

    self._build(self._filename, build_save=True, build_restore=True)

  File "D:\Anaconda3\envs\tensorflow-gpu\lib\site-packages\tensorflow\python\training\saver.py", line 1318, in _build

    raise ValueError("No variables to save")

ValueError: No variables to save