Cleaning up a bit more. Applying proper dataset label.

app.py

@@ -32,11 +32,7 @@ import torch
 
 
 # AA: Load dataset. Initial image source. 
-# Get merve/coco dataset
-from datasets import load_dataset
-
-
-#Load dataset (detection-datasets/coco)
+#Load dataset (henryscheible/coco_val2014_tiny)
 dataset = load_dataset("henryscheible/coco_val2014_tiny", split="validation")
 
 
@@ -51,14 +47,12 @@ df = pd.DataFrame(samples)
 # BB: Direct to Photos folder
 IMAGE_FOLDER = "Photos"
 
-
 image_paths = [
     os.path.join(IMAGE_FOLDER, f)
     for f in os.listdir(IMAGE_FOLDER)
     if f.lower().endswith((".jpg", ".jpeg", ".png"))
 ]
 
-
 #Load the image captioning model (Salesforce/blip-image-captioning-large)
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
 model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
@@ -86,9 +80,7 @@ def caption_random_image():
     # BB: Load into PIL - image from folder - image from folder
     image = Image.open(img_path).convert("RGB")
 
-
-
-
+    
     # AA: Image - for DF
     ##image = sample["image"]