Clean up code. Add notes (AA/BB labels)

app.py

@@ -1,12 +1,18 @@
 # Import gradio - app framework
 import gradio as gr
+
+# Two image datasources are available. 
+# Minor adjustments (add/remove # to deactivate/activate) to switch between datasources.
+# AA comments refer to images in the DataFrame / from Coco database
+# BB comments refer to images stored in local Gradio app folder
+
+# Import os and random to support random selection of image (from folder)
 import os
 import random
 
 # Import pandas datasets, transformers, torch
 import pandas as pd
-#import torch
-#import tensorflow as tf
+
 from datasets import load_dataset
 
 from transformers import (
@@ -22,6 +28,7 @@ from transformers import (
 from PIL import Image
 import torch
 
+# AA: Load dataset. Initial image source. 
 # Get merve/coco dataset
 from datasets import load_dataset
 
@@ -34,7 +41,7 @@ samples = dataset.select(range(20))
 #Convert to dataframe
 df = pd.DataFrame(samples)
 
-# Direct to Photos folder
+# BB: Direct to Photos folder
 IMAGE_FOLDER = "Photos"
 
 image_paths = [
@@ -43,10 +50,6 @@ image_paths = [
     if f.lower().endswith((".jpg", ".jpeg", ".png"))
 ]
 
-## print ("Print to show the 20 images available.")
-## print ("The app will then select an image for further exploration.")
-## print(df.head(20))
-
 #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")
@@ -57,21 +60,21 @@ trans_tokenizer = MarianTokenizer.from_pretrained(model_name)
 trans_model = MarianMTModel.from_pretrained(model_name)
 
 
-
 #Configure captioning function
+
 def caption_random_image():
 
-    # pick random row - from DF
+    # AA: pick random row - from DF
     ##sample = df.sample(1).iloc[0]
 
-    # Pick a random image path
+    # BB: Pick a random image path - image from folder
     img_path = random.choice(image_paths)
 
-    # Load into PIL
+    # BB: Load into PIL - image from folder - image from folder
     image = Image.open(img_path).convert("RGB")
 
 
-    # 'image' field contains an actual PIL image - for DF
+    # AA: Image - for DF
     ##image = sample["image"]
 
     # Unconditional image captioning