How to use numpy array instead of files when use mmdetection3d in mmdeploy

[everything]

Checklist

• I have searched related issues but cannot get the expected help.
• 2. I have read the FAQ documentation but cannot get the expected help.
• 3. The bug has not been fixed in the latest version.

Describe the bug

I successfully generated a tensorrt engine with mmdeploy using the weights and configuration from mmdetection3d. And I have successfully infer use the following code:

image = '/demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__LIDAR_TOP__1532402927647951.pcd.bin'
# build task and backend model
task_processor = build_task_processor(model_cfg, deploy_cfg, device)
model = task_processor.build_backend_model(backend_model)

# process input image
input_shape = get_input_shape(deploy_cfg)
model_inputs, _ = task_processor.create_input(image, input_shape)

# do model inference
with torch.no_grad():
    result = model.test_step(model_inputs)

I want to know how to use numpy array instead of files like image =' ...'

Reproduction

image = '/demo/data/nuscenes/n015-2018-07-24-11-22-45+0800__LIDAR_TOP__1532402927647951.pcd.bin'

Environment

as the guide

Error traceback

No response