Frozen_graph_with_def_protos不存在

Question

我目前在将SSD_Model导出到tflite时遇到问题。 我当前正在使用以下命令：

  

！python   /content/models/research/object_detection/export_tflite_ssd_graph.py —   pipeline_config_path {pipeline_fname}-受训_checkpoint_prefix   “ /content/models/research/training/model.ckpt-1000”-output_directory   “ / content / object_detection_demo /”-add_postprocessing_op True-   max_detections 10

但是它返回错误信息

liquibase

Tensorflow版本：1.15.0 Python版本：3.6.8

TIA

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