search

fuenwang / 3D-BoundingBox

PyTorch implementation for 3D Bounding Box Estimation Using Deep Learning and Geometry
130 stars 39 forks source link

Should I crop image before input my own image to the model? #7

Open championway opened 6 years ago

championway commented 6 years ago

Hi, I am trying to test some of my own images to your code, but I found that the input of your model is a crop image instead of a raw image. So does it mean that I have to do 2D bounding box with my own raw image, and then input each crop image to your model to get 3D bounding Box? I am new to deep learning, hope you won't think it is a silly question~ Thanks.

fuenwang commented 6 years ago

Yes, you should run some object detection method like faster RCNN to extract the object 2D box. For each cropped box, you should resize them to 224*224 and then apply my code.

championway commented 6 years ago

Thank you very much~