Download link to `layoutnet_ads_banner_dataset.pth.tar` missing?

When I run train.py or evaluate.py, the script always fails, probably because there is no pre-trained LayoutNet model for LayoutFID computation. Is it possible to share the weights?

Evaluating metrics...
Traceback (most recent call last):
  File "train.py", line 313, in <module>
    main() # pylint: disable=no-value-for-parameter
  File "/home/jupyter/tmp/conda_envs/layoutdetr/lib/python3.8/site-packages/click/core.py", line 1128, in __call__
    return self.main(*args, **kwargs)
  File "/home/jupyter/tmp/conda_envs/layoutdetr/lib/python3.8/site-packages/click/core.py", line 1053, in main
    rv = self.invoke(ctx)
  File "/home/jupyter/tmp/conda_envs/layoutdetr/lib/python3.8/site-packages/click/core.py", line 1395, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/home/jupyter/tmp/conda_envs/layoutdetr/lib/python3.8/site-packages/click/core.py", line 754, in invoke
    return __callback(*args, **kwargs)
  File "train.py", line 308, in main
    launch_training(c=c, desc=desc, outdir=opts.outdir, dry_run=opts.dry_run)
  File "train.py", line 99, in launch_training
    subprocess_fn(rank=0, c=c, temp_dir=temp_dir)
  File "train.py", line 47, in subprocess_fn
    training_loop.training_loop(rank=rank, **c)
  File "/home/jupyter/pending/LayoutDETR/training/training_loop.py", line 419, in training_loop
    result_dict = metric_main.calc_metric(metric=metric, run_dir=run_dir, G=snapshot_data['G_ema'],
  File "/home/jupyter/pending/LayoutDETR/metrics/metric_main.py", line 53, in calc_metric
    results = _metric_dict[metric](opts)
  File "/home/jupyter/pending/LayoutDETR/metrics/metric_main.py", line 93, in layout_fid50k_train
    layout_fid = layout_frechet_inception_distance.compute_layout_fid(opts, max_real=None, num_gen=50000)
  File "/home/jupyter/pending/LayoutDETR/metrics/layout_frechet_inception_distance.py", line 25, in compute_layout_fid
    mu_real, sigma_real = metric_utils_layout.compute_feature_stats_for_dataset(
  File "/home/jupyter/pending/LayoutDETR/metrics/metric_utils_layout.py", line 230, in compute_feature_stats_for_dataset
    detector_obj = get_feature_detector(pth=detector_pth, device=opts.device, num_gpus=opts.num_gpus, rank=opts.rank, verbose=progress.verbose)
  File "/home/jupyter/pending/LayoutDETR/metrics/metric_utils_layout.py", line 53, in get_feature_detector
    _feature_detector_cache[key] = LayoutFID(pth, device)
  File "/home/jupyter/pending/LayoutDETR/metrics/metric_layoutnet.py", line 32, in __init__
    state_dict = torch.load(pth, map_location=device)
  File "/home/jupyter/tmp/conda_envs/layoutdetr/lib/python3.8/site-packages/torch/serialization.py", line 699, in load
    with _open_file_like(f, 'rb') as opened_file:
  File "/home/jupyter/tmp/conda_envs/layoutdetr/lib/python3.8/site-packages/torch/serialization.py", line 230, in _open_file_like
    return _open_file(name_or_buffer, mode)
  File "/home/jupyter/tmp/conda_envs/layoutdetr/lib/python3.8/site-packages/torch/serialization.py", line 211, in __init__
    super(_open_file, self).__init__(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: 'pretrained/layoutnet_ads_banner_dataset.pth.tar'

Start with train.py and evaluate.py, then trace the reported failure through metrics/metric_main.py, metrics/layout_frechet_inception_distance.py, and metrics/metric_utils_layout.py. Verify how pretrained/layoutnet_ads_banner_dataset.pth.tar is expected to be obtained; done means the documented file is available at that path and LayoutFID evaluation no longer fails with FileNotFoundError.