Skip to content

wan2.2-I2V-A14B模型如何从已微调的权重中恢复训练? #1360

@MrKeee

Description

@MrKeee

请问像wan2.2-I2V-A14B这种大型的模型,我训练了几个epoch之后,想要继续恢复训练要怎么做?我看到在推理验证的脚本中是需要加载训练好的权重:
state_dict = load_state_dict("models/train/Wan2.2-I2V-A14B_high_noise_full/epoch-1.safetensors")
pipe.dit.load_state_dict(state_dict)
state_dict = load_state_dict("models/train/Wan2.2-I2V-A14B_low_noise_full/epoch-1.safetensors")
pipe.dit2.load_state_dict(state_dict)
那么需要我在恢复训练的时候,加载权重的时候也要load这个state_dict就可以了吗?

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