How to use resnet by reading the .ckpt file of my learned weights with pytorch

user_15505960 0
Viewed 423

In pytorch, how can I write the code that loads my .ckpt file instead of

model = torchvision.models.resnet50(pretrained=True)

Here is my attempt below

model = torchvision.models.resnet50(pretrained=False)

PATH = "/content/drive/MyDrive/Colab Notebooks/mlearning2/multi_logs/resnet_2/version_0/checkpoints/epoch=1-step=2543.ckpt"

model.load_state_dict(torch.load(PATH, map_location=torch.device('cpu')))

But it could not work and the following error appeared.

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...
    Unexpected key(s) in state_dict: "epoch", "global_step", "pytorch-lightning_version", "state_dict", "callbacks", "optimizer_states", "lr_schedulers", "hparams_name", "hyper_parameters".

How can I do it?

@Shai I tried to run

model.load_state_dict(torch.load(PATH, map_location=torch.device('cpu'))['state_dict'])

however got the following error. enter image description here

resnet conv-neural-network pytorch load visualization
1 Answers

Your saved checkpoint contains not only a snapshot of the trained weights of the model but some other useful information on the state of the training (e.g., the state of the optimizer etc.).

Try selecting only the relevant part of the saved checkpoint:

model.load_state_dict(torch.load(PATH, map_location=torch.device('cpu'))['state_dict'])

Update
Based on the modification you made and the new error you received, it seems like the model that was saved is model.backbone = torchvision.models.resnet50().

You need to instantiate your model in the same manner as done during training.

user_17144100
Related