PaddleDetection导出Serving模型错误

PaddlePaddle / PaddleDetection

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

Apache License 2.0

12.78k stars 2.89k forks source link

https://aistudio.baidu.com/aistudio/projectdetail/520573 使用上面的项目训练了blazeface模型，训练结果保存在work/PaddleDetection/output中。已经能够成功导出模型。然后尝试导出serving模型：

python tools/export_serving_model.py -c ../../work/blazeface.yml --output_dir=serving_model -o weights=./output/blazeface/model_final

导出后再serving_model/blazeface/serving_server文件夹下查看cat serving_client_conf.prototxt :

feed_var {
  name: "image"
  alias_name: "image"
  is_lod_tensor: false
  feed_type: 1
  shape: 3
}
fetch_var {
  name: "detection_output_0.tmp_0"
  alias_name: "detection_output_0.tmp_0"
  is_lod_tensor: false
  fetch_type: 1
  shape: 6
}

可以看到feed变量的image的shape只有3. 应该是3维变量。请问是什么问题？ AiStudio的项目能够复现问题

PaddlePaddle / PaddleDetection

PaddleDetection导出Serving模型错误 #906