apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 09:07:10 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Other]Update pptinypose python predict api with detection_result (#692)

Browse Source 
* Add pptinypose python api predict_with_detection_result

* Update keypointdetection result docs

* Update pptinypose predict api with detection_result
This commit is contained in:
huangjianhui
2022-12-19 10:20:29 +08:00
committed by GitHub
parent 81eaeddbd0
commit 75a269536a
1 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
python/fastdeploy/vision/keypointdetection/pptinypose/__init__.py
View File

@@ -41,13 +41,17 @@ class PPTinyPose(FastDeployModel):
model_format) model_format)
assert self.initialized, "PPTinyPose model initialize failed." assert self.initialized, "PPTinyPose model initialize failed."
def predict(self, input_image): def predict(self, input_image, detection_result=None):
"""Detect keypoints in an input image """Detect keypoints in an input image
:param im: (numpy.ndarray)The input image data, 3-D array with layout HWC, BGR format :param im: (numpy.ndarray)The input image data, 3-D array with layout HWC, BGR format
:param detection_result: (DetectionResult)Pre-detected boxes result, default is None
:return: KeyPointDetectionResult :return: KeyPointDetectionResult
""" """
assert input_image is not None, "The input image data is None." assert input_image is not None, "The input image data is None."
if detection_result:
return self._model.predict(input_image, detection_result)
else:
return self._model.predict(input_image) return self._model.predict(input_image)
@property @property