Closed dnap512 closed 3 years ago
The Objectron model (3D Object Detection) is a two stage detector. The first stage detects a 2D object crop using the model you linked above, while the second stage estimates the 3D bounding box from the given crop.
You can refer to the Tensorflow object detection tutorial for more information/examples.
Thank you for reply.
I am trying to use object_detection_ssd_mobilenetv2_oidv4_fp16.tflite to get 2D object crops and use them as input to the second network but the results are not meaningful. Is the model trained? If yes what dataset is used for the training?
The SSD object detector is trained on JFT.
Thanks for your response! I have two more questions and I would appreciate your response! I use Tensorflow.image.combined_non_max_suppression on detected bounding boxes to get the normalized coordinates and the label of the detected class. Now my questions are:
I recommend creating a new issue in mediapipe, as this issue is already closed.
The behavior you are describing does not sound normal. You can see the expected behavior of that graph in https://google.github.io/mediapipe/solutions/box_tracking and specifically in this graph for object detection with ssd: https://github.com/google/mediapipe/blob/master/mediapipe/graphs/tracking/subgraphs/object_detection_gpu.pbtxt.
Thanks! Sure, I'll create a new issue.
While touring the TFLite models, I found the bject_detection_ssd_mobilenetv2_oidv4_fp16.tflite file. https://github.com/google/mediapipe/blob/master/mediapipe/models/object_detection_ssd_mobilenetv2_oidv4_fp16.tflite It's not included in the description of meidiapipe models, could you tell me where to use this file?