load previous-trained model about deeptcr HOT 3 CLOSED

You can see an example of how to do inference in the tutorial under VAE inference. It should work in the same way. You instantiate a DeepTCR object with the name of the model and then run Sequence_Inference method on your data.

https://github.com/sidhomj/DeepTCR/blob/master/tutorials/unsupervised/8%20-%20VAE%20Inference.ipynb

https://sidhomj.github.io/DeepTCR/api/#DeepTCR.DeepTCR.DeepTCR_base.Sequence_Inference

Hope this helps!

from deeptcr.

Hi Dr. John William Sidhom:

Thanks for your quick response! I am sorry that I may not explain my question clearly. I went through the tutorial, and I feel like the model training and sequence inference is in the same script. In the previous step I trained a model, and in the second step I do inference using previouslt trained model.

Now suppose I want to write two scripts. In the first script, I trained a model called 'modelA', and store all middle-model-checkpoint files it at /user. Then I quit this script, and initialize another program. Now the previous modelA does not exists in the python interface, but the middle-model-checkpoint files are still there under /user. So instead of train this model again, and call the model to do inference, is there anyway to load the middle-model-checkpoint files from /user, git it a name and use it to do sequence inference?

from deeptcr.

You simply instantiate the object with the name of the model and then run the inference method you want.

DTCR = DeepTCR_SS('modelA')
DTCR.Sequence_Inference(*args)

from deeptcr.