132. Saving and Loading Our Best Performing Model (FloatTensor) error

[gauthiermartin]

Hi,

I was following along course video 132 on udemy and while trying to load back the save model I'm getting the following error in image

Here is my code :

from pathlib import Path 

# Create a model directory path
MODEL_PATH = Path("models")
MODEL_PATH.mkdir(parents=True, exist_ok=True)

# Create model save

MODEL_NAME = "03_pytorch_computer_vision_model_2.pth"

MODEL_SAVE_PATH = MODEL_PATH / MODEL_NAME

# Save the model state dict
print(f"Saving model to: {MODEL_SAVE_PATH}")
torch.save(
    obj=model_2.state_dict(),
    f=MODEL_SAVE_PATH
)

# Create a new instance 
torch.manual_seed(42)
loaded_model_2 = FashionMNISTModelV2(
    input_shape=1, 
    hidden_units=10,
    output_shape=len(class_names)
)

# Load in the saved state dict
loaded_model_2.load_state_dict(torch.load(f=MODEL_SAVE_PATH))
loaded_model_2.to(device)

# Evaluate the loaded model
torch.manual_seed(42)

loaded_model_2_results = eval_model(
    model=loaded_model_2,
    data_loader=test_dataloader,
    loss_fn=loss_fn,
    accuracy_fn=accuracy_fn
)

Here is the error output :

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
[<ipython-input-98-ce933bf213ea>](https://localhost:8080/#) in <cell line: 4>()
      2 torch.manual_seed(42)
      3 
----> 4 loaded_model_2_results = eval_model(
      5     model=loaded_model_2,
      6     data_loader=test_dataloader,

7 frames
[/usr/local/lib/python3.10/dist-packages/torch/nn/modules/conv.py](https://localhost:8080/#) in _conv_forward(self, input, weight, bias)
    457                             weight, bias, self.stride,
    458                             _pair(0), self.dilation, self.groups)
--> 459         return F.conv2d(input, weight, bias, self.stride,
    460                         self.padding, self.dilation, self.groups)
    461 

RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same or input should be a MKLDNN tensor and weight is a dense tensor

Do you have any ideas on how to solve this ?