Skip to content

Chapter 3.2.6: 关于验证代码的疑问 #468

@Zyjsjtu

Description

@Zyjsjtu
# 加载参数到网络中
load_param_into_net(net, param_dict)
# 使用函数model.predict预测image对应分类
output = model.predict(Tensor(data['image']))
# 输出预测分类与实际分类
print(f'Predicted: "{predicted[0]}", Actual: "{labels[0]}"')

Question: 导入参数之后,预测model还是沿用之前的模型吗?如果是只是想展示如何使用checkpoint加载到模型中,这里的内容也不完整?又或者Mindspore加载参数后model也会随之更新? 谢谢解答。

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions