Update dataset_utils.py

dataset_utils.py

@@ -10,4 +10,14 @@ def load_insect_dataset():
 def preprocess_image(image_path):
     processor = ViTImageProcessor.from_pretrained("google/vit-base-patch16-224")
     image = Image.open(image_path).convert("RGB")
-    return processor(image, return_tensors="pt")
+    return processor(image, return_tensors="pt")
+
+def load_species_descriptions():
+    # BIOSCAN-5M example structure: replace with actual implementation as needed
+    species_data = load_dataset("Gharaee/BIOSCAN-5M")
+    descriptions = {}
+    for record in species_data["train"]:
+        species_name = record.get("species_name", "Unknown Species")
+        description = record.get("description", "No description available.")
+        descriptions[species_name] = description
+    return descriptions