Negative values in the predicted annotations

[vipul43]

This is a screenshot of the image that I tried to make predictions in using model.predict_jsons functions, but the resultant annotations of this function have negative bbox values. There are two faces detected in the image, in the sequence I have added the annotations below, second prediction bbox has negative values. I checked the image, the image is good. Only the predictions of the get_model with max_size=2048, is resulting in such predictions

[vipul43]

Also, what is the max_size parameter to the get_model function...?? Is it the maximum size of the input image?

[woctezuma]

Also, what is the max_size parameter to the get_model function...?? Is it the maximum size of the input image?

This parameter is used to resize the image. It is the target length for the longest side of the image.

Same as in: https://github.com/xinntao/facexlib/blob/45fee8e7885fc462d2d4c4eafb2650ff384b89c8/facexlib/detection/retinaface.py#L171-L183