stroblme
1e62e77aed
It claimed to run the pipeline with no engine involved, and could not: the node bodies it called save and load artifacts, which raise outside a node by design. Each node is now a thin wrapper over a plain function — make_rows, train_curve, score — and __main__ calls those, which is the split the sandbox already demonstrates and the one worth copying.
52 lines
1.7 KiB
Python
52 lines
1.7 KiB
Python
"""Which nodes make up which flow.
|
|
|
|
Membership is this list, not the file a function sits in: `fit` is declared in
|
|
`train.py` and used by both flows below, once as itself and once rewired and
|
|
reconfigured. Wiring is not membership either — nodes connect because one
|
|
provides a message another requires, never because one imported the other.
|
|
|
|
fluksio sync examples/myresearch
|
|
fluksio run train --lr 0.05 --wait
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from fluksio import Flow, Port, use
|
|
from myresearch.data import augment, make_rows, prepare
|
|
from myresearch.evaluate import evaluate, score
|
|
from myresearch.train import fit, train_curve
|
|
|
|
train = Flow(
|
|
"train",
|
|
title="Train",
|
|
nodes=[prepare, fit, evaluate],
|
|
inputs=[Port("lr", "float", initial=0.01)],
|
|
outputs=["score", "final_loss"],
|
|
)
|
|
|
|
finetune = Flow(
|
|
"finetune",
|
|
title="Finetune",
|
|
nodes=[
|
|
prepare,
|
|
augment,
|
|
# The same function, reading `augmented` instead of `dataset` and with
|
|
# a shorter schedule. `train` is unaffected.
|
|
use(fit, wire={"dataset": "augmented"}, epochs=3),
|
|
evaluate,
|
|
],
|
|
inputs=[Port("lr", "float", initial=0.0001)],
|
|
outputs=["score"],
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
# Run the research here, with no engine involved. Not the node bodies: they
|
|
# save and load artifacts, and there is nothing to save to out here. The
|
|
# functions they wrap are ordinary Python, which is why they are worth
|
|
# keeping separate — the arithmetic stays yours to run by hand.
|
|
data = make_rows(limit=64)
|
|
print("rows:", len(data["rows"]))
|
|
print("losses:", [round(loss, 4) for loss in train_curve(0.05, 5)])
|
|
print("score:", score(0.05, 5))
|