You can not select more than 25 topics
Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
chenjunyu
7702eed03c
|
9 months ago | |
|---|---|---|
| .. | ||
| README.md | 9 months ago | |
| mask_rcnn_r50_fpn_sample1e-3_mstrain_2x_lvis.py | 9 months ago | |
| mask_rcnn_r101_fpn_sample1e-3_mstrain_2x_lvis.py | 9 months ago | |
| mask_rcnn_x101_32x4d_fpn_sample1e-3_mstrain_2x_lvis.py | 9 months ago | |
| mask_rcnn_x101_64x4d_fpn_sample1e-3_mstrain_2x_lvis.py | 9 months ago | |
README.md
LVIS dataset
Introduction
@inproceedings{gupta2019lvis,
title={{LVIS}: A Dataset for Large Vocabulary Instance Segmentation},
author={Gupta, Agrim and Dollar, Piotr and Girshick, Ross},
booktitle={Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition},
year={2019}
}
Common Setting
- Please follow install guide to install open-mmlab forked cocoapi first.
- Run following scripts to install our forked lvis-api.
pip install "git+https://github.com/open-mmlab/cocoapi.git#subdirectory=lvis" - All experiments use oversample strategy here with oversample threshold
1e-3. - The size of LVIS v0.5 is half of COCO, so schedule
2xin LVIS is roughly the same iterations as1xin COCO.
Results and models
| Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Download |
|---|---|---|---|---|---|---|---|
| R-50-FPN | pytorch | 2x | - | - | 26.1 | 25.9 | model | log |
| R-101-FPN | pytorch | 2x | - | - | 27.1 | 27.0 | model | log |
| X-101-32x4d-FPN | pytorch | 2x | - | - | 26.7 | 26.9 | model | log |
| X-101-64x4d-FPN | pytorch | 2x | - | - | 26.4 | 26.0 | model | log |
