assert self._width is not None and self._height is not None

[ma3252788]

Hello, thank you very much for your work. I first trained for 2 epochs, then started the test, and the result reported an error:

loading annotations into memory...
Done (t=0.32s)
creating index...
index created!
saved                                                                                                                                                                                                              
Traceback (most recent call last):
  File "demo_opt.py", line 472, in <module>
    eval_results = _evaluate_predictions_on_crowdhuman(gt_path, fpath)
  File "demo_opt.py", line 448, in _evaluate_predictions_on_crowdhuman
    database = Database(gt_path, dt_path, target_key, None, mode)
  File "demo_opt.py", line 312, in __init__
    self.loadData(dtpath, body_key, head_key, if_gt=False)
  File "demo_opt.py", line 331, in loadData
    self.images[record["ID"]].clip_all_boader()
  File "demo_opt.py", line 195, in clip_all_boader
    assert self._width is not None and self._height is not None
AssertionError

I followed the instructions completely, but why did it report an error?

[zyayoung]

We embed the width and height info in the annotation file. You may try the following script to do this.

import json

from tqdm import tqdm
from PIL import Image

src = '/data/datasets/crowdhuman/annotation_val.odgt'
dst = '/data/datasets/crowdhuman/annotation_val_hw.odgt'
img_path = '/data/datasets/crowdhuman/train_image/'

with open(src, 'r') as f:
    lines = f.readlines()

with open(dst, 'w') as f:
    for line in tqdm(lines):
        record = json.loads(line)
        file_path = img_path + '{}.jpg'.format(record['ID'])
        im = Image.open(file_path)
        record['width'], record['height'] = im.size
        f.write(json.dumps(record) + "\n")

Sorry for the inconvenience.