Giters

tjqansthd / LapDepth-release

Monocular Depth Estimation Using Laplacian Pyramid-Based Depth Residuals

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

To avoid warning in pytorch 2.0.0 during inference

leizhenyu-lzy opened this issue · comments

commented

use

self.encoder = models.resnext101_32x8d(weights=models.ResNeXt101_32X8D_Weights.IMAGENET1K_V1)

instead of

self.encoder = models.resnext101_32x8d(pretrained=True)

in order to avoid warning like following

/home/lzy/miniconda3/envs/lane/lib/python3.8/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(
/home/lzy/miniconda3/envs/lane/lib/python3.8/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=ResNeXt101_32X8D_Weights.IMAGENET1K_V1`. You can also use `weights=ResNeXt101_32X8D_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)