Update app.py

app.py

@@ -1,7 +1,7 @@
-import torch
-import gradio as gr 
+import torch 
 import re 
-from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel
+import gradio as gr
+from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel 
 
 device='cpu'
 encoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
@@ -11,6 +11,7 @@ feature_extractor = ViTFeatureExtractor.from_pretrained(encoder_checkpoint)
 tokenizer = AutoTokenizer.from_pretrained(decoder_checkpoint)
 model = VisionEncoderDecoderModel.from_pretrained(model_checkpoint).to(device)
 
+
 def predict(image,max_length=64, num_beams=4):
   image = image.convert('RGB')
   image = feature_extractor(image, return_tensors="pt").pixel_values.to(device)
@@ -19,32 +20,25 @@ def predict(image,max_length=64, num_beams=4):
   caption_text = clean_text(tokenizer.decode(caption_ids))
   return caption_text 
 
-def set_example_image(example: list) -> dict:
-    return gr.Image.update(value=example[0])
-css = '''
-h1#title {
-  text-align: center;
-}
-h3#header {
-  text-align: center;
-}
-img#overview {
-  max-width: 800px;
-  max-height: 600px;
-}
-img#style-image {
-  max-width: 1000px;
-  max-height: 600px;
-}
-'''
-demo = gr.Blocks(css=css)
-with demo:
-  gr.Markdown('''<h1 id="title">Image Caption 🖼️</h1>''')
-  gr.Markdown('''Made by : Shreyas Dixit''')
-  with gr.Column():
-        input = gr.inputs.Image(label="Upload your Image", type = 'pil', optional=True)
-        output = gr.outputs.Textbox(type="auto",label="Captions")
-  btn = gr.Button("Genrate Caption")
-  btn.click(fn=predict, inputs=input, outputs=output)
-
-demo.launch()
+
+
+input = gr.inputs.Image(label="Upload your Image", type = 'pil', optional=True)
+output = gr.outputs.Textbox(type="auto",label="Captions")
+examples = [f"example{i}.jpg" for i in range(1,7)]
+
+description= "Image captioning application made using transformers"
+title = "Image Captioning 🖼️"
+
+article = "Created By : Shreyas Dixit "
+
+interface = gr.Interface(
+        fn=predict,
+        inputs = input,
+        theme="grass",
+        outputs=output,
+        examples = examples,
+        title=title,
+        description=description,
+        article = article,
+    )
+interface.launch(debug=True)