search

zwx8981 / LIQE

[CVPR2023] Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective
MIT License
194 stars 11 forks source link

raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for CLIP: Missing key(s) in state_dict: "positional_embedding", "text_projection", "logit_scale", "visual.class_embedding", "visual.positional_embedding", "visual.proj", "visual.conv1.weight", "visual.ln_pre.weight", "visual.ln_pre.bias", "visual.transformer.resblocks.0.attn.in_proj_weight", #15

Closed zhang1483 closed 11 months ago

zhang1483 commented 11 months ago

raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for CLIP: Missing key(s) in state_dict: "positional_embedding", "text_projection", "logit_scale", "visual.class_embedding", "visual.positional_embedding", "visual.proj", "visual.conv1.weight", "visual.ln_pre.weight", "visual.ln_pre.bias", "visual.transformer.resblocks.0.attn.in_proj_weight", 训练之后的权重放入demo，会出现模型不匹配的问题是为什么，自己训练的权重参数比作者给的大。

zwx8981 commented 11 months ago

训练时除了模型权重还会保存优化器状态等，你torch.load之后要用'model_state_dict'作为key把模型权重提取出来然后再载入模型。

routll commented 11 months ago

训练时除了模型权重还会保存优化器状态等，你torch.load之后要用'model_state_dict'作为key把模型权重提取出来，然后再载入模型。

谢谢大神！！！解决了！

hjb25286 commented 1 month ago

训练时除了模型权重还会保存优化器状态等，你torch.load之后要用'model_state_dict'作为key把模型权重提取出来然后再载入模型。

RuntimeError: Expected 4-dimensional input for 4-dimensional weight [768, 3, 32, 32], but got 5-dimensional input of size [15, 468, 3, 224, 224] instead 这样修改之后，出现这种错误，请问您有什么解决方法吗

zwx8981 commented 1 month ago

@hjb25286 这个问题跟model load无关，请提供更详细的描述