RuntimeError: "replication_pad2d_cuda" not implemented for 'BFloat16'

[jiafengshen]

RuntimeError: "replication_pad2d_cuda" not implemented for 'BFloat16'？
help! when I run {
import torch
import cv2
import numpy as np
from mdm.model.v2 import MDMModel

Load model

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = MDMModel.from_pretrained('robbyant/lingbot-depth-pretrain-vitl-14-v0.5').to(device)

Load and prepare inputs

image = cv2.cvtColor(cv2.imread('examples/0/rgb.png'), cv2.COLOR_BGR2RGB)
h, w = image.shape[:2]
image = torch.tensor(image / 255, dtype=torch.float32, device=device).permute(2, 0, 1)[None]

depth = cv2.imread('examples/0/raw_depth.png', cv2.IMREAD_UNCHANGED).astype(np.float32) / 1000.0
depth = torch.tensor(depth, dtype=torch.float32, device=device)[None]

intrinsics = np.loadtxt('examples/0/intrinsics.txt')
intrinsics[0] /= w # Normalize fx and cx by width
intrinsics[1] /= h # Normalize fy and cy by height
intrinsics = torch.tensor(intrinsics, dtype=torch.float32, device=device)[None]

Run inference

output = model.infer(
image,
depth_in=depth,
intrinsics=intrinsics)

depth_pred = output['depth'] # Refined depth map
points = output['points'] # 3D point cloud}