预训练模型导致的问题 --预训练模型上传的时候没有上传成功

最新推荐文章于 2023-12-17 15:48:32 发布

原创最新推荐文章于 2023-12-17 15:48:32 发布 · 3.6k 阅读

4 ·

CC 4.0 BY-SA版权

深度学习同时被 2 个专栏收录

22 篇文章

订阅专栏

python 小程序

21 篇文章

订阅专栏

该错误源于尝试加载的预训练模型参数与当前模型的参数形状不符。具体表现为多个卷积层权重、下采样层权重及归一化层参数的形状不一致，例如layer1.0和layer1.1的conv1.weight，以及其他层的downsample权重和偏置等。问题可能出在模型定义或预训练模型的加载过程中。

部署运行你感兴趣的模型镜像

mismatch for layer1.0.conv1.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]).

size mismatch for layer1.1.conv1.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]).

由于预训练模型导致的问题 --预训练模型上传的时候没有上传成功

size mismatch for layer3.0.conv1.weight: copying a param with shape torch.Size([256, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 512, 1, 1]).
size mismatch for layer3.0.downsample.0.weight: copying a param with shape torch.Size([256, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 512, 1, 1]).
size mismatch for layer3.0.downsample.1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for layer3.0.downsample.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for layer3.0.downsample.1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for layer3.0.downsample.1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for layer3.1.conv1.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]).
size mismatch for layer4.0.conv1.weight: copying a param with shape torch.Size([512, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 1024, 1, 1]).
size mismatch for layer4.0.downsample.0.weight: copying a param with shape torch.Size([512, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([2048, 1024, 1, 1]).
size mismatch for layer4.0.downsample.1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([2048]).
size mismatch for layer4.0.downsample.1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([2048]).
size mismatch for layer4.0.downsample.1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([2048]).
size mismatch for layer4.0.downsample.1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([2048]).
size mismatch for layer4.1.conv1.weight: copying a param with shape torch.Size([512, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 2048, 1, 1]).

这个错误产生的原因是：应该是预训练模型与参数不匹配首先我们查看下：

"/project/train/src_repo/deep_net/ResNet-PyTorch-master/examples/imagenet/resnet_pytorch/model.py

size mismatch for layer1.0.conv1.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]).
size mismatch for layer1.1.conv1.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]).

size mismatch for layer2.0.conv1.weight: copying a param with shape torch.Size([128, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 256, 1, 1]).
size mismatch for layer2.0.downsample.0.weight: copying a param with shape torch.Size([128, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 256, 1, 1]).

size mismatch for layer2.0.downsample.1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for layer2.0.downsample.1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for layer2.0.downsample.1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for layer2.0.downsample.1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for layer2.1.conv1.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 512, 1, 1]).