Hi, thanks for this example. I'm fairly new to this, and thought I'd try out the seq2seq-translation-batched example. It includes the statements...
Requirements
You will need PyTorch to build and train the models, and matplotlib for plotting training and visualizing attention outputs later. The rest are builtin Python libraries.
This is incorrect; something called 'sconce' is required as well, but doesn't get imported until farther down in the notebook. (NOTE: 'visdom' is also required, even further down.)
Hi, thanks for this example. I'm fairly new to this, and thought I'd try out the seq2seq-translation-batched example. It includes the statements...
This is incorrect; something called 'sconce' is required as well, but doesn't get imported until farther down in the notebook. (NOTE: 'visdom' is also required, even further down.)
After locating and installing sconce (https://github.com/davidlmorton/pytorch-sconce,
pip install pytorch-sconce
), we find that it's loaded with f-strings, and thus will only run in Python 3.6, (EDIT: there's also https://github.com/asottile/future-fstrings).So, upgrading everything to Python 3.6, we now get the message...
Not sure where to go from here. How do you get this to work? Thanks.