Taskflow 无法指定显卡

[kg-nlp]

您好：

wordtag = Taskflow("knowledge_mining", model="wordtag", device_id=3,task_path="./custom_task_path/",linking=False) 指定显卡序列3 但在程序运行时仍然要判断0号显卡 Please check whether there is any other process using GPU 0.

1. If yes, please stop them, or start PaddlePaddle on another GPU.
2. If no, please decrease the batch size of your model.

使用环境 paddlenlp 2.2.3 paddlepaddle 2.2.1

[linjieccc]

您好，unset CUDA_VISIBLE_DEVICES后再试下呢

[kg-nlp]

您好，仍然存在问题

`[2022-01-21 09:09:58,123] [ INFO] - Already cached /home/zhangyj-n/.paddlenlp/models/wordtag/vocab.txt [2022-01-21 09:09:58,158] [ INFO] - Already cached /home/zhangyj-n/.paddlenlp/models/wordtag/wordtag_pos.pdparams W0121 09:09:58.161566 184825 device_context.cc:447] Please NOTE: device: 2, GPU Compute Capability: 7.5, Driver API Version: 10.1, Runtime API Version: 10.1 W0121 09:09:58.169664 184825 device_context.cc:465] device: 2, cuDNN Version: 7.6. [2022-01-21 09:10:05,785] [ INFO] - Converting to the inference model cost a little time. [2022-01-21 09:10:09,733] [ INFO] - The inference model save in the path:./custom_task_path/static/inference

InvalidArgumentError: The start row index must be less than the end row index.But received the start index = 1, the end index = 1. [Hint: Expected begin_idx < end_idx, but received begin_idx:1 >= end_idx:1.] (at /paddle/paddle/fluid/framework/tensor.cc:120) [operator < viterbi_decode > error]`

[kg-nlp]

设置为device_id = 0 程序正常运行

[a101269]

我也遇到同样问题

[linjieccc]

@joey12300 辛苦帮忙看下这个问题

[github-actions[bot]]

This issue is stale because it has been open for 60 days with no activity. 当前issue 60天内无活动，被标记为stale。

[github-actions[bot]]

This issue was closed because it has been inactive for 14 days since being marked as stale. 当前issue 被标记为stale已有14天，即将关闭。