TimesFM(Time Series Foundation Model)安装简介
readme
在Window 上安装并执行出现报错,
{
"name": "TypeError",
"message": "TimesFmBase.__init__() got an unexpected keyword argument 'context_len'",
"stack": "---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
Cell In[9], line 8
3 from jax._src import config
4 config.update(
5 \"jax_platforms\", {\"cpu\": \"cpu\", \"gpu\": \"cuda\", \"tpu\": \"\"}[timesfm_backend]
6 )
----> 8 model = timesfm.TimesFm(
9 context_len=512,
10 horizon_len=128,
11 input_patch_len=32,
12 output_patch_len=128,
13 num_layers=20,
14 model_dims=1280,
15 backend=timesfm_backend,
16 )
17 model.load_from_checkpoint(repo_id=\"google/timesfm-1.0-200m\")
TypeError: TimesFmBase.__init__() got an unexpected keyword argument 'context_len'"
}
决定在 小红帽ubuntu UBUNTU
安装 timesFM
在 ide.cloud.tencent.com 的环境上进行安装 环境
We recommend at least 16GB RAM to load TimesFM dependencies.
慎选环境,确保>16G
安装Conda 3.10 python
重要步骤 安装 pyenv and poetry
## Installation
### Local installation using poetry
We will be using `pyenv` and `poetry`. In order to set these things up please follow the instructions [here](https://substack.com/home/post/p-148747960?r=28a5lx&utm_campaign=post&utm_medium=web). Note that the PAX (or JAX) version needs to run on python 3.10.x and the PyTorch version can run on >=3.11.x. Therefore make sure you have two versions of python installed:
确认已经完成安装
(base) root@VM-0-170-ubun

最低0.47元/天 解锁文章
1277

被折叠的 条评论
为什么被折叠?



