-
Notifications
You must be signed in to change notification settings - Fork 4
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This all looks good to me, I just had a few clarifying questions to make sure I understood it. I think I'm still trying to get my head around the code architecture a little bit
m = LSTMModel(10, 3) | ||
|
||
# %% | ||
m.load_weights("../../2a_model/out/models/0_baseline_LSTM/train_weights/") |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'm a little confused where these weights come from
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
These are weights produced by the snakemake workflow:
directory("{outdir}/train_weights/"), |
m.load_weights("../../2a_model/out/models/0_baseline_LSTM/train_weights/") | ||
|
||
# %% | ||
data = np.load("../../2a_model/out/models/0_baseline_LSTM/prepped.npz", allow_pickle=True) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Also confused here as to what you are loading, are these input data to use for plotting
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes these are input data. They are used to just run the model once so I can get the weight values. ... now that I think of it, I'm not 100% sure this step is necessary.
This PR is code used to look into:
Specifically the code