Atsushi Saito
04/18/2022, 11:05 AM@dagster.graph
def preprocess(context):
# do ELT in multi nodes CPU cluster at this graph
# Push data into a s3 bucket
@dagster.graph
def train_model(context, s3bucket_to_preprocessed_data):
# Train in GPU or TPU cluster at this graph
# Save model file and push into s3bucket and then publish s3bucket path of model files into pub/sub messaging for each epoch
# e.g. A value of a topic is "<s3://model-bin/epoch_001>"
@dagster.graph
def infer_model(context, s3bucket_to_validation_data, s3bucket_to_model_file)
# Subscribe s3bucket path from the above messaging topic.
# Evaluate the model in a cluster which is not the one for preprocess graph and train_model graph.
@dagster.graph
def entire_train_and_eval_job(context):
# Run the above three graphs once in a while.
Atsushi Saito
04/18/2022, 1:58 PMZach
04/18/2022, 2:21 PMAtsushi Saito
04/19/2022, 11:17 AMZach
04/19/2022, 5:21 PM