Python Scripts for 3D Object Detection

google-research-datasets / Objectron

Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes

Other

2.22k stars 264 forks source link

Python Scripts for 3D Object Detection #72

Open HripsimeS opened 1 year ago

HripsimeS commented 1 year ago

@ahmadyan Hi Adel,

Where we can find a code for the training of models and code for testing on inference dataset? Thanks in advance!

Hripsime

ahmadyan commented 1 year ago

We have not released the training code, but we did release the pre-trained models (both in Mediapipe, as well as the Objectron bucket on GCS).
The python evaluation code is located here. The eval script uses the ground truth bounding boxes.
Python and Web API for Objectron models (available via Mediapipe, Python colab). Objectron models now offer a ready-to-use yet customizable Python solution as part of the prebuilt Mediapipe Python package. The Mediapipe Python package is available on PyPI for Linux, macOS and Windows.

HripsimeS commented 1 year ago

@ahmadyan thanks a lot for your answer. If I want to do a training of a new object that does not exist in your pre-trained models, I would need also a training code. Is there any way to receive it or it is forbidden to have an access?