Skip to content

Latest commit

 

History

History
85 lines (68 loc) · 3.47 KB

File metadata and controls

85 lines (68 loc) · 3.47 KB

Data and Weights Preparation

This guide walks you through preparing datasets and pretrained weights required for HERMES.


1. Prepare nuScenes Dataset


2. Prepare Text Annotations


3. Prepare Pretrained Weights

a) Download InternVL-2 Pretraining

cd projects/mmdet3d_plugin/models/internvl_chat
mkdir pretrained
cd pretrained
huggingface-cli download --resume-download --local-dir-use-symlinks False OpenGVLab/InternVL2-2B --local-dir InternVL2-2B

b) Download Project Checkpoints


Directory Structure

Your project directory should look like this after setup:

HERMES
├── data
│   ├── nuscenes
│   │   ├── mask_cam_img.jpg
│   │   ├── nuscenes_advanced_12Hz_infos_train.pkl
│   │   ├── nuscenes_masked_only_infos_temporal_train.pkl
│   │   ├── nuscenes_infos_temporal_train.pkl
│   │   └── nuscenes_infos_temporal_val.pkl
│   ├── omnidrive_nusc
│   └── NuInteractCaption
├── ckpt
│   ├── open_clip_convnext_base_w-320_laion_aesthetic-s13B-b82k.bin
│   ├── hermes_stage1.pth
│   ├── hermes_stage2_1.pth
│   ├── hermes_stage2_2.pth
│   └── hermes_final.pth

Please refer to Usage.md for instructions on HERMES training and evaluation.