按照教程导出的模型，导入出错 about paddledetection HOT 6 CLOSED

强制转换就行了 im_info= np.array([800.,800.,1.], dtype='float32')

from paddledetection.

@aixier 请给下导出模型时的运行命令，注意模型要加载通过指定weights正确设置~

[inference_program, feed_target_names, fetch_targets] = fluid.io.load_inference_model(dirname=save_freeze_dir, executor=exe)

中最好指定下 model_filename 和 params_filename的名字。

from paddledetection.

python tools/export_model.py -c configs/dcn/cascade_rcnn_dcn_r50_fpn_1x.yml --output_dir=./inference_model_cas -o weights=/home/aistudio/work/PaddleDetection/ResNet50_cos_pretrained.tar YoloTestFeed.image_shape=[3,448,448] @qingqing01

from paddledetection.

@aixier 保存模型选错了，请注意选择cascade_rcnn_dcn_r50_fpn_1x对应的模型是:
https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_dcn_r50_fpn_1x.tar

另外:

[inference_program, feed_target_names, fetch_targets] = fluid.io.load_inference_model(dirname=save_freeze_dir, executor=exe)

中最好指定下 model_filename 和 params_filename的名字。

from paddledetection.

可以load了
[inference_program, feed_target_names, fetch_targets] = fluid.io.load_inference_model(dirname=path, executor=exe, model_filename="model", params_filename="params")
但是设置： im_info= np.array([800.,800.,1.])
然后
batch_outputs = exe.run(inference_program,
feed={feed_target_names[0]: tensor_img,
feed_target_names[1]: im_info,
feed_target_names[2]: image_shape[np.newaxis, :]},
fetch_list=fetch_targets,
return_numpy=False)

会报错
PaddleCheckError: Tensor holds the wrong type, it holds double, but desires to be float at [D:\1.6.1\paddle\paddle/fluid
/framework/tensor_impl.h:30]
@qingqing01

from paddledetection.

@aixier 既然解决了，那就close了

from paddledetection.