Pytorch 0.3加载0.4模型

Posted 2020-12-30 ranjiewen

- pytorch0.4有一些接口已经改变，且模型向下版本兼容，不向上兼容。

• In PyTorch 0.4, is it recommended to use `reshape` than `view` when it is possible?
• Question about ‘rebuild_tensor_v2‘?

使用pytorch0.3导入pytorch0.4保存的模型时候:

 Monkey-patch because I trained with a newer version.
# This can be removed once PyTorch 0.4.x is out.
# See https://discuss.pytorch.org/t/question-about-rebuild-tensor-v2/14560
import torch._utils
try:
    torch._utils._rebuild_tensor_v2
except AttributeError:
    def _rebuild_tensor_v2(storage, storage_offset, size, stride, requires_grad, backward_hooks):
        tensor = torch._utils._rebuild_tensor(storage, storage_offset, size, stride)
        tensor.requires_grad = requires_grad
        tensor._backward_hooks = backward_hooks
        return tensor
    torch._utils._rebuild_tensor_v2 = _rebuild_tensor_v2

• 拷贝一些权重到新的模型方法，感觉不能直接抽取sequential里面的某一层，除非重新构建模型，forward得到该层的内容，或者使用hook操作；
• pytorch在fintune时将sequential中的层输出，以vgg为例