2d_fashion_landmark.md 5.0 KB

2D Fashion Landmark Dataset

It is recommended to symlink the dataset root to $MMPOSE/data. If your folder structure is different, you may need to change the corresponding paths in config files.

MMPose supported datasets:

DeepFashion (Fashion Landmark Detection, FLD)

DeepFashion (CVPR'2016)
@inproceedings{liuLQWTcvpr16DeepFashion,
 author = {Liu, Ziwei and Luo, Ping and Qiu, Shi and Wang, Xiaogang and Tang, Xiaoou},
 title = {DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations},
 booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 month = {June},
 year = {2016}
}

DeepFashion (ECCV'2016)
@inproceedings{liuYLWTeccv16FashionLandmark,
 author = {Liu, Ziwei and Yan, Sijie and Luo, Ping and Wang, Xiaogang and Tang, Xiaoou},
 title = {Fashion Landmark Detection in the Wild},
 booktitle = {European Conference on Computer Vision (ECCV)},
 month = {October},
 year = {2016}
 }

For DeepFashion dataset, images can be downloaded from download. Please download the annotation files from fld_annotations. Extract them under {MMPose}/data, and make them look like this:

mmpose
├── mmpose
├── docs
├── tests
├── tools
├── configs
`── data
    │── fld
        │-- annotations
        │   │-- fld_upper_train.json
        │   |-- fld_upper_val.json
        │   |-- fld_upper_test.json
        │   │-- fld_lower_train.json
        │   |-- fld_lower_val.json
        │   |-- fld_lower_test.json
        │   │-- fld_full_train.json
        │   |-- fld_full_val.json
        │   |-- fld_full_test.json
        │-- img
        │   │-- img_00000001.jpg
        │   │-- img_00000002.jpg
        │   │-- img_00000003.jpg
        │   │-- img_00000004.jpg
        │   │-- img_00000005.jpg
        │   │-- ...

DeepFashion2

DeepFashion2 (CVPR'2019)
@article{DeepFashion2,
  author = {Yuying Ge and Ruimao Zhang and Lingyun Wu and Xiaogang Wang and Xiaoou Tang and Ping Luo},
  title={A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images},
  journal={CVPR},
  year={2019}
}

For DeepFashion2 dataset, images can be downloaded from download. Please download the annotation files. These annotation files are converted by deepfashion2_to_coco.py. Extract them under {MMPose}/data, and make them look like this:

mmpose
├── mmpose
├── docs
├── tests
├── tools
├── configs
`── data
    │── deepfashion2
        │── train
            │-- deepfashion2_short_sleeved_outwear_train.json
            │-- deepfashion2_short_sleeved_dress_train.json
            │-- deepfashion2_skirt_train.json
            │-- deepfashion2_sling_dress_train.json
            │-- ...
            │-- image
            │   │-- 000001.jpg
            │   │-- 000002.jpg
            │   │-- 000003.jpg
            │   │-- 000004.jpg
            │   │-- 000005.jpg
            │   │-- ...
        │── validation
            │-- deepfashion2_short_sleeved_dress_validation.json
            │-- deepfashion2_long_sleeved_shirt_validation.json
            │-- deepfashion2_trousers_validation.json
            │-- deepfashion2_skirt_validation.json
            │-- ...
            │-- image
            │   │-- 000001.jpg
            │   │-- 000002.jpg
            │   │-- 000003.jpg
            │   │-- 000004.jpg
            │   │-- 000005.jpg
            │   │-- ...