VictorMylle/Thesis
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Updated thesis

Browse Source
This commit is contained in:
Victor Mylle
2024-05-18 11:58:45 +02:00
parent 8a219d0d19
commit 5c365ebd88
8 changed files with 16 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/trainers/trainer.py
View File

@@ -114,8 +114,8 @@ class Trainer:
predict_sequence_length=self.model.output_size, full_day_skip=True
)
train_loader, test_loader = self.data_processor.get_dataloaders(
predict_sequence_length=self.model.output_size
train_loader, val_loader, test_loader = self.data_processor.get_dataloaders(
predict_sequence_length=self.model.output_size, validation=True
)
train_samples = self.random_samples(train=True, num_samples=5)
@@ -146,7 +146,7 @@ class Trainer:
running_loss += loss.item()
running_loss /= len(train_loader.dataset)
test_loss = self.test(test_loader)
test_loss = self.test(val_loader)
if self.patience is not None:
if (
@@ -170,7 +170,7 @@ class Trainer:
)
task.get_logger().report_scalar(
title=self.criterion.__class__.__name__,
series="test",
series="val",
value=test_loss,
iteration=epoch,
)
@@ -194,7 +194,7 @@ class Trainer:
# )
if hasattr(self, "calculate_crps_from_samples"):
self.calculate_crps_from_samples(task, test_loader, epoch)
self.calculate_crps_from_samples(task, val_loader, epoch)
if task:
self.finish_training(task=task)

8
src/training_scripts/diffusion_training.py
View File

@@ -2,9 +2,9 @@ from src.utils.clearml import ClearMLHelper
clearml_helper = ClearMLHelper(project_name="Thesis/NrvForecast")
task = clearml_helper.get_task(
task_name="Diffusion Training: hidden_sizes=[512, 512] (100 steps), lr=0.0001, time_dim=8",
task_name="Diffusion Training: hidden_sizes=[1024, 1024] (300 steps), all features",
)
# task.execute_remotely(queue_name="default", exit_process=True)
task.execute_remotely(queue_name="default", exit_process=True)
from src.models import *
from src.losses import *
@@ -42,7 +42,7 @@ print("Input dim: ", inputDim)
model_parameters = {
"epochs": 15000,
"learning_rate": 0.0001,
"hidden_sizes": [512, 512],
"hidden_sizes": [1024, 1024],
"time_dim": 8,
}
@@ -71,6 +71,6 @@ policy_evaluator = PolicyEvaluator(baseline_policy, task)
#### Trainer ####
trainer = DiffusionTrainer(
model, data_processor, "cuda", policy_evaluator=policy_evaluator, noise_steps=20
model, data_processor, "cuda", policy_evaluator=policy_evaluator, noise_steps=300
)
trainer.train(model_parameters["epochs"], model_parameters["learning_rate"], task)