From b06dad23affeaa2495f694c99d7b5849b3292d8c Mon Sep 17 00:00:00 2001 From: Falko Habel Date: Fri, 21 Feb 2025 21:47:06 +0100 Subject: [PATCH] downsized samples to max of 10k --- src/aiunn/finetune.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/aiunn/finetune.py b/src/aiunn/finetune.py index e29d36d..10cedba 100644 --- a/src/aiunn/finetune.py +++ b/src/aiunn/finetune.py @@ -13,7 +13,7 @@ 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(10000) + df = pd.read_parquet(parquet_file, columns=['image_512', 'image_1024']).head(5000) combined_df = pd.concat([combined_df, df], ignore_index=True) # Validate data format