Open ysh-strive opened 3 years ago
the number in class_name.txt is not matched
(1)deep部分的权重能提供下?还是deep部分原来的ckpt.t7文件 (2)能提供下详细的复现步骤和文件? 目前出现下面错误: RuntimeError: Error(s) in loading state_dict for Net: size mismatch for classifier.4.weight: copying a param with shape torch.Size([751, 256]) from checkpoint, the shape in current model is torch.Size([10, 256]). size mismatch for classifier.4.bias: copying a param with shape torch.Size([751]) from checkpoint, the shape in current model is torch.Size([10]). 请问你解决了吗?怎么解决的,遇到了同样的问题
尺度不匹配,调整成你模型的类别数。
---原始邮件--- 发件人: @.> 发送时间: 2021年9月4日 11:03:10 收件人: @.>; 抄送: @.**@.>; 主题: Re: [deyiwang89/pytorch-yolov4-deepsort] 运行时的问题 (#3)
(1)deep部分的权重能提供下?还是deep部分原来的ckpt.t7文件 (2)能提供下详细的复现步骤和文件? 目前出现下面错误: RuntimeError: Error(s) in loading state_dict for Net: size mismatch for classifier.4.weight: copying a param with shape torch.Size([751, 256]) from checkpoint, the shape in current model is torch.Size([10, 256]). size mismatch for classifier.4.bias: copying a param with shape torch.Size([751]) from checkpoint, the shape in current model is torch.Size([10]). 请问你解决了吗?怎么解决的,遇到了同样的问题
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.
(1)deep部分的权重能提供下?还是deep部分原来的ckpt.t7文件 (2)能提供下详细的复现步骤和文件? 目前出现下面错误: RuntimeError: Error(s) in loading state_dict for Net: size mismatch for classifier.4.weight: copying a param with shape torch.Size([751, 256]) from checkpoint, the shape in current model is torch.Size([10, 256]). size mismatch for classifier.4.bias: copying a param with shape torch.Size([751]) from checkpoint, the shape in current model is torch.Size([10]).