| \n | detect_result_list = self.predictor.predict(np_image) | \n
| \n | if self.padder and detect_result_list: | \n
| \n | boxes = np.array([detect_result.box for detect_result in detect_result_list]) | \n
| \n | boxes_orig = self.padder.inverse_apply_coords(boxes) | \n
| \n | for idx, detect_result in enumerate(detect_result_list): | \n
| \n | detect_result.box = boxes_orig[idx, :].tolist() | \n
| \n | \n |
| \n | for detect_result in detect_result_list: | \n
| \n | self.dp_manager.set_image_annotation(detect_result, to_image=self.to_image, crop_image=self.crop_image) | \n
Raw results from predictors are not being kept in memory.
","upvoteCount":1,"url":"https://github.com/deepdoctection/deepdoctection/discussions/364#discussioncomment-10670203"}}}Are the results stored in memory?? #364
-
|
How can I use the "detect result list" of image layout out the layout.py. Are they stored some where in memory?? |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment 1 reply
-
|
Raw results from predictors (e.g. 'DetectionResult') will be validated and converted into some derived deepdoctection/deepdoctection/pipe/layout.py Lines 90 to 98 in b975421 Raw results from predictors are not being kept in memory. |
Beta Was this translation helpful? Give feedback.
-
|
yeah okay @JaMe76. Thank you for clarification. |
Beta Was this translation helpful? Give feedback.
Raw results from predictors (e.g. 'DetectionResult') will be validated and converted into some derived
Annotationinstance. You can see a snippet in the code below:self.dp_manager.set_image_annotationwill do the validation and the conversion into the target format.deepdoctection/deepdoctection/pipe/layout.py
Lines 90 to 98 in b975421