New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
InceptionTime Model for Time Series #256
Conversation
Have to fix a couple of issues with the residual part. |
Hey @ToucheSir @darsnack @lorenzoh, |
Try building up your model bit-by-bit and checking for size mismatches on each submodule with a dummy input. |
Yeah I tried doing that. I dont understand how the forward pass works fine but the backprop gives an error. Will figure it out. |
Since only
|
The code can be tested with the following snipet :- data, blocks = load(datarecipes()["natops"]);
task = TSClassificationSingle(blocks, data);
traindl, validdl = taskdataloaders(data, task, 16);
callbacks = [ToGPU(), Metrics(accuracy)];
model = FastTimeSeries.Models.InceptionTime(24, 6);
learner = Learner(model, tasklossfn(task); data=(traindl, validdl), optimizer=ADAM(), callbacks = [ToGPU(), Metrics(accuracy)]);
fitonecycle!(learner, 10, 0.01) |
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.
Just a couple comments on the WIP here. Mostly looks good and I'm glad you can get it training :)
bottleneck_block = bottleneck ? Conv1d(ni, nf, 1, bias = false) : identity | ||
|
||
convs_layers = | ||
[Conv1d(bottleneck ? nf : ni, nf, ks[i], bias = false) for i in range(1, stop = 3)] |
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 think it makes more sense to have Conv1d
be lowercase conv1d
, but that's a minor thing.
Hey guys, so the model is working for regression task too now, will push the notebook in a while. |
I have some suggestions for the notebook, but that can wait for a follow-up PR. Will try to have a look at the model again in the next couple of days. |
inception = [] | ||
shortcut = [] | ||
|
||
for d in range(1, stop = depth) |
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.
Still many wild range
s floating around ;)
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.
Yeah, will fix that in the next commit.
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.
Mostly LGTM once docstrings are added and commented code is restored/removed.
3c51c9d
to
67a989a
Compare
Hey, will push the docstrings today. This PR should be ready to go after it unless we want to further improve something. We can also discuss the future steps in our next biweekly. |
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.
Sorry about the delay on reviewing this. Let's get it merged.
This PR will contain the implementation of InceptionTime Model and it's use for classification and regression task.
Some of the commits from the PR #253 are also in this PR, but will take care of them when that PR is merged.