-
Notifications
You must be signed in to change notification settings - Fork 109
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
Fix Check Failed Error #585
Conversation
if count != input_count: | ||
logger.warning( | ||
f"{type(cls._deployable_module_model.oneflow_module)} input count changed, will reload graph. " | ||
f"When setting the strength parameter in the 'Apply ControlNet' node, please exercise caution. " |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这个说明不太通用。可以当前使用输入的 tensor 的个数是否变化来判断是否要重新编译一个图,当前出现了变化,所以会新编译一个图。
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
修改为 f"Module {type(self._deployable_module_model.oneflow_module)} input tensor count changed from {count} to {input_count}, will compile again."
self._deployable_module_dpl_graph = None | ||
self._load_graph_first_run = True | ||
|
||
self._deployable_module_input_count = input_count |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
只有 count != input_count 才更新 _deployable_module_input_count ?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
已修改为 只有 count != input_count 才更新 _deployable_module_input_count
修改 因为模型输入参数数量改变的 check failed 行为,目前 发现模型输入参数数量改变,让其重新加载图文件。