python - freeze_graph_with_def_protos 不存在

Question

我目前在将 SSD_Model 导出到 tflite 时遇到问题。我目前正在使用这个命令：

!python /content/models/research/object_detection/export_tflite_ssd_graph.py — pipeline_config_path {pipeline_fname} —trained_checkpoint_prefix “/content/models/research/training/model.ckpt-1000” — output_directory “/content/object_detection_demo/” — add_postprocessing_op True —最大检测数 10

但它返回一个错误说

Traceback (most recent call last):
  File "/content/models/research/object_detection/export_tflite_ssd_graph.py", line 143, in <module>
    tf.compat.v1.app.run(main)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/platform/app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 299, in run
    _run_main(main, args)
  File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 250, in _run_main
    sys.exit(main(argv))
  File "/content/models/research/object_detection/export_tflite_ssd_graph.py", line 139, in main
    FLAGS.max_classes_per_detection, use_regular_nms=FLAGS.use_regular_nms)
  File "/content/models/research/object_detection/export_tflite_ssd_graph_lib.py", line 306, in export_tflite_graph
    initializer_nodes='')
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/tools/freeze_graph.py", line 129, in freeze_graph_with_def_protos
    "' doesn't exist!")
ValueError: Input checkpoint '' doesn't exist!

TensorFlow 版本：1.15.0 Python 版本：3.6.8

TIA

标签： pythontensorflow

Answer 1

我找到了解决方案，只需将文件的实际位置如下所示

!python /content/models/research/object_detection/export_tflite_ssd_graph.py \
--pipeline_config_path /content/models/research/object_detection/samples/configs/ssd_mobilenet_v2_coco.config \
--trained_checkpoint_prefix /content/models/research/training/model.ckpt-206 \
--output_directory /content/object_detection_demo/ \
add_postprocessing_op True \
--max_detections 10