updates

data_curation.py

@@ -21,7 +21,7 @@ def take_random_sample(dataset):
     """Take a sample from the dataset"""
     return dataset.take(size=10,seed=51)
 
-def prepare_dataset(name):
+def prepare_dataset(name="Voxel51/Data-Centric-Visual-AI-Challenge-Train-Set"):
     """
     Prepare the dataset for model training.
     
@@ -57,5 +57,4 @@ def prepare_dataset(name):
     dataset = take_random_sample(dataset)
     
     # Return the curated dataset
-    curated_dataset = dataset.clone() 
-    return curated_dataset
+    curated_dataset = dataset.clone(name="curated_dataset")

script.py

@@ -12,16 +12,13 @@ Your predictions must be in a label_field called "predictions" in the dataset.
 See here for more details about hyperparameters for this model: https://docs.ultralytics.com/modes/train/#train-settings
 """
 import os
-from datetime import datetime
-from math import log
+
 import yaml
 
 import fiftyone as fo
 import fiftyone.utils.random as four
 import fiftyone.utils.huggingface as fouh
 
-from ultralytics import YOLO
-
 from data_curation import prepare_dataset
 
 def export_to_yolo_format(
@@ -68,7 +65,10 @@ def train_model(training_dataset, training_config):
     """
     Train the YOLO model on the given dataset using the provided configuration.
     """
-    print("Starting the training process...")
+    training_dataset = fouh.load_from_hub(
+        "Voxel51/Data-Centric-Visual-AI-Challenge-Train-Set",
+        max_samples=100 #for testing remove this later
+        )
 
     print("Splitting the dataset...")
     four.random_split(training_dataset, {"train": training_config['train_split'], "val": training_config['val_split']})