Update app.py

app.py

@@ -45,6 +45,7 @@ clip_processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
 
 # Load the Unsplash dataset
 dataset = load_dataset("jamescalam/unsplash-25k-photos", split="train")  # all 25K images are in train split
+dataset_size = len(dataset)
 
 # Load gpt and modifed weights for captions
 gpt = GPT2LMHeadModel.from_pretrained('gpt2')
@@ -229,7 +230,7 @@ with gr.Blocks() as demo:
         1. Enter list of labels separated by commas (or select one of the examples below)
         2. Click **Get Random Image** to grab a random image from dataset
         3. Click **Classify Image** to analyze current image against the labels (including after changing labels)
-        4. The dataset (<a href="https://github.com/unsplash/datasets" target="_blank">Unsplash Lite</a>) contains 25,000 nature-focused images"""
+        """
         gr.Markdown(instructions)
         with gr.Row(variant="compact"):
             label_text = gr.Textbox(show_label=False, placeholder="Enter classification labels").style(container=False)
@@ -253,15 +254,17 @@ with gr.Blocks() as demo:
         get_btn.click(fn=rand_image, outputs=im)
         #im.change(predict, inputs=[im, labels], outputs=cf)
         class_btn.click(predict, inputs=[im, labels], outputs=cf)
+        gr.HTML(f"Dataset: <a href='https://github.com/unsplash/datasets' target='_blank'>Unsplash Lite</a>; Number of Images: {dataset_size}")
+    
 
     with gr.Tab("Captioning"):
         instructions = """## Instructions:
         1. Click **Get Random Image** to grab a random image from dataset
         1. Click **Create Caption** to generate a caption for the image
         1. Different models can be selected:
-        * **COCO** generally produces more straight-forward captions, but it is a smaller dataset and therefore struggles to recognize certain objects
-        * **Conceptual Captions** is a much larger dataset but sometimes produces overly ``poetic'' results
-        1. The dataset (<a href="https://github.com/unsplash/datasets" target="_blank">Unsplash Lite</a>) contains 25,000 nature-focused images"""
+           * **COCO** generally produces more straight-forward captions, but it is a smaller dataset and therefore struggles to recognize certain objects
+           * **Conceptual Captions** is a much larger dataset but sometimes produces results that resemble social media posts
+        """
         gr.Markdown(instructions)
         with gr.Row():
             with gr.Column(variant="panel"):
@@ -274,12 +277,13 @@ with gr.Blocks() as demo:
         get_btn_cap.click(fn=rand_image, outputs=im_cap)
         #im_cap.change(generate_text, inputs=im_cap, outputs=caption)
         caption_btn.click(get_caption, inputs=[im_cap, model_name], outputs=caption)
+        gr.HTML(f"Dataset: <a href='https://github.com/unsplash/datasets' target='_blank'>Unsplash Lite</a>; Number of Images: {dataset_size}")
 
     with gr.Tab("Search"):
         instructions = """## Instructions:
         1. Enter a search query (or select one of the examples below)
         2. Click **Find Images** to find images that match the query (top 5 are shown in order from left to right)
-        3. The dataset (<a href="https://github.com/unsplash/datasets" target="_blank">Unsplash Lite</a>) contains 25,000 nature-focused images"""
+        3. Keep in mind that the dataset contains mostly nature-focused images"""
         gr.Markdown(instructions)
         with gr.Column(variant="panel"):
             desc = gr.Textbox(show_label=False, placeholder="Enter description").style(container=False)
@@ -292,5 +296,6 @@ with gr.Blocks() as demo:
             search_btn = gr.Button("Find Images").style(full_width=False)
         gallery = gr.Gallery(show_label=False).style(grid=(2,2,3,5))
         search_btn.click(search,inputs=desc, outputs=gallery, postprocess=False)
+        gr.HTML(f"Dataset: <a href='https://github.com/unsplash/datasets' target='_blank'>Unsplash Lite</a>; Number of Images: {dataset_size}")
 
 demo.launch()