c522de9b0411ebafd18c685aca6a7a93bf1cf061,train.py,,,#,134

Before Change

    // your_imgs_file_list, your_objs_info_list, your_mask_list, your_targets = \
    //     get_pose_data_list(config.DATA.your_images_path, config.DATA.your_annos_path)
    //// 2. if you have a folder with many folders: (which is common in industry)
    folder_list = tl.files.load_folder_list(path="your_data")
    your_imgs_file_list, your_objs_info_list, your_mask_list = [], [], []
    for folder in folder_list:
        _imgs_file_list, _objs_info_list, _mask_list, _targets = \
            get_pose_data_list(os.path.join(folder, "images"), os.path.join(folder, "coco.json"))
        print(len(_imgs_file_list))
        your_imgs_file_list.extend(_imgs_file_list)
        your_objs_info_list.extend(your_objs_info_list)
        your_mask_list.extend(your_mask_list)
    print("number of customized images found:", len(your_imgs_file_list))

After Change

            path="data", dataset="2017", task="person")

    //// read coco training images contains valid people
    train_imgs_file_list, train_objs_info_list, train_mask_list, train_targets = \
        get_pose_data_list(train_im_path, train_ann_path)

    //// read coco validating images contains valid people (you can use it for training as well)
    val_imgs_file_list, val_objs_info_list, val_mask_list, val_targets = \
        get_pose_data_list(train_im_path, train_ann_path)

Instances