# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license

# SKU-110K retail items dataset https://github.com/eg4000/SKU110K_CVPR19 by Trax Retail
# Documentation: https://docs.ultralytics.com/datasets/detect/sku-110k/
# Example usage: yolo train data=SKU-110K.yaml
# parent
# ├── ultralytics
# └── datasets
#     └── SKU-110K ← downloads here (13.6 GB)

# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: SKU-110K # dataset root dir
train: train.txt # train images (relative to 'path') 8219 images
val: val.txt # val images (relative to 'path') 588 images
test: test.txt # test images (optional) 2936 images

# Classes
names:
  0: object

# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
  import shutil
  from pathlib import Path

  import numpy as np
  import polars as pl

  from ultralytics.utils import TQDM
  from ultralytics.utils.downloads import download
  from ultralytics.utils.ops import xyxy2xywh

  # Download
  dir = Path(yaml["path"])  # dataset root dir
  parent = Path(dir.parent)  # download dir
  urls = ["http://trax-geometry.s3.amazonaws.com/cvpr_challenge/SKU110K_fixed.tar.gz"]
  download(urls, dir=parent)

  # Rename directories
  if dir.exists():
      shutil.rmtree(dir)
  (parent / "SKU110K_fixed").rename(dir)  # rename dir
  (dir / "labels").mkdir(parents=True, exist_ok=True)  # create labels dir

  # Convert labels
  names = "image", "x1", "y1", "x2", "y2", "class", "image_width", "image_height"  # column names
  for d in "annotations_train.csv", "annotations_val.csv", "annotations_test.csv":
      x = pl.read_csv(dir / "annotations" / d, has_header=False, new_columns=names, infer_schema_length=None).to_numpy()  # annotations
      images, unique_images = x[:, 0], np.unique(x[:, 0])
      with open((dir / d).with_suffix(".txt").__str__().replace("annotations_", ""), "w", encoding="utf-8") as f:
          f.writelines(f"./images/{s}\n" for s in unique_images)
      for im in TQDM(unique_images, desc=f"Converting {dir / d}"):
          cls = 0  # single-class dataset
          with open((dir / "labels" / im).with_suffix(".txt"), "a", encoding="utf-8") as f:
              for r in x[images == im]:
                  w, h = r[6], r[7]  # image width, height
                  xywh = xyxy2xywh(np.array([[r[1] / w, r[2] / h, r[3] / w, r[4] / h]]))[0]  # instance
                  f.write(f"{cls} {xywh[0]:.5f} {xywh[1]:.5f} {xywh[2]:.5f} {xywh[3]:.5f}\n")  # write label