Machine-Learning
/
aiuNN
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

even more downsized

This commit is contained in:
Falko Victor Habel 2025-02-22 10:45:30 +01:00
parent f576a0d789
commit 90bcdd346a
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/aiunn/finetune.py
View File

@ -15,7 +15,7 @@ class UpscaleDataset(Dataset):
combined_df = pd.DataFrame()
for parquet_file in parquet_files:
# Load data with chunking for memory efficiency
df = pd.read_parquet(parquet_file, columns=['image_512', 'image_1024']).head(2500)
df = pd.read_parquet(parquet_file, columns=['image_512', 'image_1024']).head(1250)
combined_df = pd.concat([combined_df, df], ignore_index=True)
# Validate data format
@ -94,7 +94,7 @@ from torch.utils.data import DataLoader
# Create your dataset and dataloader
dataset = UpscaleDataset(["/root/training_data/vision-dataset/image_upscaler.parquet", "/root/training_data/vision-dataset/image_vec_upscaler.parquet"], transform=transform)
data_loader = DataLoader(dataset, batch_size=2, shuffle=True)
data_loader = DataLoader(dataset, batch_size=1, shuffle=True)
# Define a loss function and optimizer
criterion = nn.MSELoss()