如何通过 pytorch 加载预训练的 model？ (mm时尚)

Question

import io

import torch
import torch.nn as nn
from torchvision import models
from PIL import Image
import torchvision.transforms as transforms

checkpoint_path = 'C:/venvs/ai/aiproduct/latest.pth'
pretrained_weights = torch.load(checkpoint_path, map_location='cpu', strict=False)

model = models.resnet50(pretrained=True)
model.load_state_dict(pretrained_weights)

这带来

TypeError: 'strict' is an invalid keyword argument for load()

和

import io

import torch
import torch.nn as nn
from torchvision import models
from PIL import Image
import torchvision.transforms as transforms

checkpoint_path = 'C:/venvs/ai/aiproduct/latest.pth'
pretrained_weights = torch.load(checkpoint_path, map_location='cpu')

model = models.resnet50(pretrained=True)
model.load_state_dict(pretrained_weights)
# model.eval()
print(model)
# model.summary()

如果我摆脱“严格”

Traceback (most recent call last):
  File "c:\venvs\ai\aiproduct\test.py", line 13, in <module>
    model.load_state_dict(pretrained_weights)
  File "C:\Python39\lib\site-packages\torch\nn\modules\module.py", line 1223, in load_state_dict
    raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for ResNet:
        Missing key(s) in state_dict: "conv1.weight", "bn1.weight", "bn1.bias", "bn1.running_mean", "bn1.running_var", "layer1.0.conv1.weight", "layer1.0.bn1.weight", "layer1.0.bn1.bias", "layer1.0.bn1.running_mean", "layer1.0.bn1.running_var", "layer1.0.conv2.weight", "layer1.0.bn2.weight", "layer1.0.bn2.bias", "layer1.0.bn2.running_mean", "layer1.0.bn2.running_var", "layer1.0.conv3.weight", "layer1.0.bn3.weight", "layer1.0.bn3.bias", "layer1.0.bn3.running_mean", "layer1.0.bn3.running_var", "layer1.0.downsample.0.weight", "layer1.0.downsample.1.weight", "layer1.0.downsample.1.bias", "layer1.0.downsample.1.running_mean", "layer1.0.downsample.1.running_var", "layer1.1.conv1.weight", "layer1.1.bn1.weight", "layer1.1.bn1.bias", "layer1.1.bn1.running_mean", "layer1.1.bn1.running_var", "layer1.1.conv2.weight", "layer1.1.bn2.weight", "layer1.1.bn2.bias", "layer1.1.bn2.running_mean", 
"layer1.1.bn2.running_var", "layer1.1.conv3.weight", "layer1.1.bn3.weight", "layer1.1.bn3.bias", "layer1.1.bn3.running_mean", "layer1.1.bn3.running_var", "layer1.2.conv1.weight", "layer1.2.bn1.weight", "layer1.2.bn1.bias", "layer1.2.bn1.running_mean", "layer1.2.bn1.running_var", "layer1.2.conv2.weight", "layer1.2.bn2.weight", "layer1.2.bn2.bias", "layer1.2.bn2.running_mean", "layer1.2.bn2.running_var", "layer1.2.conv3.weight", "layer1.2.bn3.weight", "layer1.2.bn3.bias", "layer1.2.bn3.running_mean", "layer1.2.bn3.running_var", "layer2.0.conv1.weight", "layer2.0.bn1.weight", "layer2.0.bn1.bias", "layer2.0.bn1.running_mean", "layer2.0.bn1.running_var", "layer2.0.conv2.weight", "layer2.0.bn2.weight", "layer2.0.bn2.bias", "layer2.0.bn2.running_mean", "layer2.0.bn2.running_var", "layer2.0.conv3.weight", "layer2.0.bn3.weight", "layer2.0.bn3.bias", "layer2.0.bn3.running_mean", "layer2.0.bn3.running_var", "layer2.0.downsample.0.weight", "layer2.0.downsample.1.weight", "layer2.0.downsample.1.bias", "layer2.0.downsample.1.running_mean", "layer2.0.downsample.1.running_var", "layer2.1.conv1.weight", "layer2.1.bn1.weight", "layer2.1.bn1.bias", "layer2.1.bn1.running_mean", "layer2.1.bn1.running_var", "layer2.1.conv2.weight", "layer2.1.bn2.weight", "layer2.1.bn2.bias", "layer2.1.bn2.running_mean", "layer2.1.bn2.running_var", "layer2.1.conv3.weight", "layer2.1.bn3.weight", "layer2.1.bn3.bias", "layer2.1.bn3.running_mean", "layer2.1.bn3.running_var", "layer2.2.conv1.weight", "layer2.2.bn1.weight", "layer2.2.bn1.bias", "layer2.2.bn1.running_mean", "layer2.2.bn1.running_var", "layer2.2.conv2.weight", "layer2.2.bn2.weight", "layer2.2.bn2.bias", "layer2.2.bn2.running_mean", "layer2.2.bn2.running_var", "layer2.2.conv3.weight", "layer2.2.bn3.weight", "layer2.2.bn3.bias", "layer2.2.bn3.running_mean", "layer2.2.bn3.running_var", "layer2.3.conv1.weight", "layer2.3.bn1.weight", "layer2.3.bn1.bias", "layer2.3.bn1.running_mean", "layer2.3.bn1.running_var", "layer2.3.conv2.weight", "layer2.3.bn2.weight", "layer2.3.bn2.bias", "layer2.3.bn2.running_mean", "layer2.3.bn2.running_var", "layer2.3.conv3.weight", "layer2.3.bn3.weight", "layer2.3.bn3.bias", "layer2.3.bn3.running_mean", "layer2.3.bn3.running_var", "layer3.0.conv1.weight", "layer3.0.bn1.weight", "layer3.0.bn1.bias", "layer3.0.bn1.running_mean", "layer3.0.bn1.running_var", "layer3.0.conv2.weight", "layer3.0.bn2.weight", "layer3.0.bn2.bias", "layer3.0.bn2.running_mean", "layer3.0.bn2.running_var", "layer3.0.conv3.weight", "layer3.0.bn3.weight", "layer3.0.bn3.bias", "layer3.0.bn3.running_mean", "layer3.0.bn3.running_var", "layer3.0.downsample.0.weight", "layer3.0.downsample.1.weight", "layer3.0.downsample.1.bias", "layer3.0.downsample.1.running_mean", "layer3.0.downsample.1.running_var", "layer3.1.conv1.weight", "layer3.1.bn1.weight", "layer3.1.bn1.bias", "layer3.1.bn1.running_mean", "layer3.1.bn1.running_var", "layer3.1.conv2.weight", "layer3.1.bn2.weight", "layer3.1.bn2.bias", "layer3.1.bn2.running_mean", "layer3.1.bn2.running_var", "layer3.1.conv3.weight", "layer3.1.bn3.weight", "layer3.1.bn3.bias", "layer3.1.bn3.running_mean", "layer3.1.bn3.running_var", "layer3.2.conv1.weight", "layer3.2.bn1.weight", "layer3.2.bn1.bias", "layer3.2.bn1.running_mean", "layer3.2.bn1.running_var", "layer3.2.conv2.weight", "layer3.2.bn2.weight", "layer3.2.bn2.bias", "layer3.2.bn2.running_mean", "layer3.2.bn2.running_var", "layer3.2.conv3.weight", "layer3.2.bn3.weight", "layer3.2.bn3.bias", "layer3.2.bn3.running_mean", "layer3.2.bn3.running_var", "layer3.3.conv1.weight", "layer3.3.bn1.weight", "layer3.3.bn1.bias", "layer3.3.bn1.running_mean", "layer3.3.bn1.running_var", "layer3.3.conv2.weight", "layer3.3.bn2.weight", "layer3.3.bn2.bias", "layer3.3.bn2.running_mean", "layer3.3.bn2.running_var", "layer3.3.conv3.weight", "layer3.3.bn3.weight", "layer3.3.bn3.bias", "layer3.3.bn3.running_mean", "layer3.3.bn3.running_var", "layer3.4.conv1.weight", "layer3.4.bn1.weight", "layer3.4.bn1.bias", "layer3.4.bn1.running_mean", "layer3.4.bn1.running_var", "layer3.4.conv2.weight", "layer3.4.bn2.weight", "layer3.4.bn2.bias", "layer3.4.bn2.running_mean", "layer3.4.bn2.running_var", "layer3.4.conv3.weight", "layer3.4.bn3.weight", "layer3.4.bn3.bias", "layer3.4.bn3.running_mean", "layer3.4.bn3.running_var", 
"layer3.5.conv1.weight", "layer3.5.bn1.weight", "layer3.5.bn1.bias", "layer3.5.bn1.running_mean", "layer3.5.bn1.running_var", "layer3.5.conv2.weight", "layer3.5.bn2.weight", "layer3.5.bn2.bias", "layer3.5.bn2.running_mean", "layer3.5.bn2.running_var", "layer3.5.conv3.weight", "layer3.5.bn3.weight", "layer3.5.bn3.bias", "layer3.5.bn3.running_mean", "layer3.5.bn3.running_var", "layer4.0.conv1.weight", "layer4.0.bn1.weight", "layer4.0.bn1.bias", "layer4.0.bn1.running_mean", "layer4.0.bn1.running_var", "layer4.0.conv2.weight", "layer4.0.bn2.weight", "layer4.0.bn2.bias", "layer4.0.bn2.running_mean", "layer4.0.bn2.running_var", "layer4.0.conv3.weight", "layer4.0.bn3.weight", "layer4.0.bn3.bias", "layer4.0.bn3.running_mean", "layer4.0.bn3.running_var", "layer4.0.downsample.0.weight", "layer4.0.downsample.1.weight", "layer4.0.downsample.1.bias", "layer4.0.downsample.1.running_mean", "layer4.0.downsample.1.running_var", "layer4.1.conv1.weight", "layer4.1.bn1.weight", "layer4.1.bn1.bias", "layer4.1.bn1.running_mean", "layer4.1.bn1.running_var", "layer4.1.conv2.weight", "layer4.1.bn2.weight", "layer4.1.bn2.bias", "layer4.1.bn2.running_mean", "layer4.1.bn2.running_var", "layer4.1.conv3.weight", "layer4.1.bn3.weight", "layer4.1.bn3.bias", 
"layer4.1.bn3.running_mean", "layer4.1.bn3.running_var", "layer4.2.conv1.weight", "layer4.2.bn1.weight", "layer4.2.bn1.bias", "layer4.2.bn1.running_mean", "layer4.2.bn1.running_var", "layer4.2.conv2.weight", "layer4.2.bn2.weight", "layer4.2.bn2.bias", "layer4.2.bn2.running_mean", "layer4.2.bn2.running_var", "layer4.2.conv3.weight", "layer4.2.bn3.weight", "layer4.2.bn3.bias", "layer4.2.bn3.running_mean", "layer4.2.bn3.running_var", "fc.weight", "fc.bias".
        Unexpected key(s) in state_dict: "meta", "state_dict", "optimizer".

我应该怎么办？

I just want to make some cloth attribute predicting web app with pretrained model (mmfashion https://github.com/open-mmlab/mmfashion/blob/master/docs/MODEL_ZOO.md ) but I fail to use pretrained model.

Answer 1

假设您下载了wide_resnet50_2的权重，并且执行了与您下载的权重训练相同的任务：

import torchvision
model = torchvision.models.wide_resnet50_2(pretrained=True)

for param in model.parameters():
    param.required_grad = False

然后您下载的参数可以加载为：

加载 model state 字典

model.load_state_dict(torch.load('./C:/venvs/ai/aiproduct/latest.pth')) # path of your weights
model.eval()
model.cuda()

Answer 2

这个预训练的 model 你有什么成功吗？ 我也在用这个框架做一个项目..