pytorch model loading and prediction, AttributeError: 'dict' object has no attribute 'predict'

Question

model = torch.load('/home/ofsdms/san_mrc/checkpoint/best_v1_checkpoint.pt', map_location='cpu')
results, labels = predict_function(model, dev_data, version)

> /home/ofsdms/san_mrc/my_utils/data_utils.py(34)predict_squad()
-> phrase, spans, scores = model.predict(batch)
(Pdb) n
AttributeError: 'dict' object has no attribute 'predict'

How do I load a saved checkpoint of pytorch model, and use the same for prediction. I have the model saved in .pt extension

Shai · Accepted Answer · 2019-05-06 09:55:52Z

1

the checkpoint you save is usually a state_dict: a dictionary containing the values of the trained weights - but not the actual architecture of the net. The actual computational graph/architecture of the net is described as a python class (derived from nn.Module).
To use a trained model you need:

Instantiate a model from the class implementing the computational graph.

Load the saved state_dict to that instance:

model.load_state_dict(torch.load('/home/ofsdms/san_mrc/checkpoint/best_v1_checkpoint.pt', map_location='cpu')

answered May 6, 2019 at 9:55

Shai

115k39 gold badges259 silver badges398 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

vinsent paramanantham Over a year ago

I have used torch.load to do a full model load, in my case, model = DocReaderModel(opt, embedding) model_file_2 = os.path.join(model_dir, 'checkpoint_{}_epoch_{}_full_model.pt'.format(version, epoch)), torch.save(model, model_file_2)

Collectives™ on Stack Overflow

pytorch model loading and prediction, AttributeError: 'dict' object has no attribute 'predict'

1 Answer 1

1 Comment

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

1 Comment

Your Answer

Sign up or log in

Post as a guest

Related