ImageToDepth¶

class agentlego.tools.ImageToDepth(device='cuda', toolmeta=None)[源代码]

A tool to estimation depth of an image.

参数:

device (str) – The device to load the model. Defaults to ‘cuda’.
device – The device to load the model. Defaults to ‘cuda’.
toolmeta (None | dict | ToolMeta) – The additional info of the tool. Defaults to None.

默认工具信息¶

名称: ImageToDepth
描述: This tool can generate the depth image of an image.
输入:
- image (ImageIO)
输出:
- ImageIO

Examples¶

Use the tool directly (without agent)

from agentlego.apis import load_tool

# load tool
tool = load_tool('ImageToDepth', device='cuda')

# apply tool
depth = tool('examples/demo.png')
print(depth)

With Lagent

from lagent import ReAct, GPTAPI, ActionExecutor
from agentlego.apis import load_tool

# load tools and build agent
# please set `OPENAI_API_KEY` in your environment variable.
tool = load_tool('ImageToDepth', device='cuda').to_lagent()
agent = ReAct(GPTAPI(temperature=0.), action_executor=ActionExecutor([tool]))

# agent running with the tool.
img_path = 'examples/demo.png'
ret = agent.chat(f'Please estimate the depth of the image `{img_path}`')
for step in ret.inner_steps[1:]:
    print('------')
    print(step['content'])

Set up¶

Before using the tool, please confirm you have installed the related dependencies by the below commands.

pip install -U transformers

Reference¶

This tool uses a DPT model in default settings. See the following paper for details.

@article{DBLP:journals/corr/abs-2103-13413,
  author    = {Ren{\'{e}} Ranftl and
               Alexey Bochkovskiy and
               Vladlen Koltun},
  title     = {Vision Transformers for Dense Prediction},
  journal   = {CoRR},
  volume    = {abs/2103.13413},
  year      = {2021},
  url       = {https://arxiv.org/abs/2103.13413},
  eprinttype = {arXiv},
  eprint    = {2103.13413},
  timestamp = {Wed, 07 Apr 2021 15:31:46 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2103-13413.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}