-
Notifications
You must be signed in to change notification settings - Fork 5.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
【论文复现】模型动转静报错: Input(Ids) of LookupTableV2Op should not be null #43225
Comments
你好,方便提供下完整的动转静导出运行命令吗? |
你好,动转静的导出命令为: |
|
另外有个问题想要请教下,代码会走到 |
是的,需要将compute_loss设置为False |
ifelse配合dict使用的问题修复PR #43348 已经合入develop分支。 |
导出模型和推理的代码都在:https://github.com/Mixture-of-Rookie/UNITER-Paddle |
您好,我目前已经完成了TIPC的整个流程,只差GPU下的推理了。 我在GPU下的推理中遇到了如下的错误:
|
问题描述 Please describe your issue
运行环境:
Python 3.6
paddlepaddle-gpu 2.3.0
模型由动态图模式转为静态图的时候,报如下的错:
动转静代码:
https://github.com/Mixture-of-Rookie/UNITER-Paddle/blob/main/export_model.py
模型组网代码:
https://github.com/Mixture-of-Rookie/UNITER-Paddle/blob/main/models/uniter.py#L184
具体报错如下:
尝试如下:
调试输出 input_ids, 发现不是null
The text was updated successfully, but these errors were encountered: