Inference with PyTorch
Here are the steps to use Galileo for Inference with a text classification model.
- 1.Initialize the Galileo project - Use the
dq.initfunction to initialize the Galileo project. The function takes three arguments: the project type, the project name, and the run name.
- 2.Log the inference data - Use the
dq.log_datasetfunction to log the inference data. The function takes two arguments: the inference data and the split name.
- 3.Set the class labels - Use the
dq.set_labels_for_runfunction to set the class labels for the run. The function takes one argument: the names of the classes.
- 4.Set the split to inference with
- 5.Monitor the model - Use the
watchfunction from the Galileo's PyTorch integration to monitor the model. The function takes two arguments: the model and the dataloader.
- 6.Run the model on the data using the data loader
- 7.Finish the run - Use the
dq.finishfunction to finish the run.
Once the training is complete in the console you select the inference dataset as your subset in the top right corner.