How should I use Uni3D to train multiple datasets？

[YangBo0411]

First of all, thank you for your outstanding contribution to 3D object detection. As can see from the paper, you don't directly perform dataset-level merging. I'm currently working on cross-domain multi-dataset training in 2D and would like to learn from your ideas from Uni3D. I would like to know how I can run uni3D to train multiple datasets (what specific code to call on the terminal, or what specific .py file to run.), and I'd like to know how you fed multiple datasets separately into the network training.

[BOBrown]

@YangBo0411 Thanks for your approval towards.

For performing the multi-dataset training using Uni3D, you could refer to train a Uni3D detection model on the merged dataset for the training script, refor to train_multi_db.py for training code, and refer to uni3d config file for experimental setting file.

[BOBrown]

@YangBo0411

For your issue of how to merge multi-datasets, you could merge two batches from different datasets using common_utils.merge_two_batch_dict(batch_1, batch_2). Please refer to here