Update app.py

app.py

@@ -2,6 +2,8 @@ import torch
 import re 
 import gradio as gr
 from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel 
+from transformers import AutoProcessor, AutoTokenizer, BlipForConditionalGeneration
+from huggingface_hub import hf_hub_download
 
 device='cpu'
 encoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
@@ -18,12 +20,47 @@ def predict(image,max_length=64, num_beams=4):
   clean_text = lambda x: x.replace('<|endoftext|>','').split('\n')[0]
   caption_ids = model.generate(image, max_length = max_length)[0]
   caption_text = clean_text(tokenizer.decode(caption_ids))
-  return caption_text 
+  caption_text2 = generate_caption(image)
+  return caption_text, caption_text2
+
+blip_processor_large = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
+blip_model_large = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
+
+blip_model_large.to(device)
+
+
+def generate_caption(processor, model, image, tokenizer=None, use_float_16=False):
+    inputs = processor(images=image, return_tensors="pt").to(device)
+
+    if use_float_16:
+        inputs = inputs.to(torch.float16)
+    
+    generated_ids = model.generate(pixel_values=inputs.pixel_values, max_length=50)
+
+    if tokenizer is not None:
+        generated_caption = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    else:
+        generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+   
+    return generated_caption
+
+
+
+def generate_captions(image):
+
+
+    caption_blip_large = generate_caption(blip_processor_large, blip_model_large, image)
+
+
+    return caption_blip_large
 
 
 
 input = gr.inputs.Image(label="Upload your Image", type = 'pil', optional=True)
-output = gr.outputs.Textbox(type="text",label="Captions")
+#Two output boxes
+
+output_1 = gr.outputs.Textbox(type="text",label="Caption - 1")
+output_2 = gr.outputs.Textbox(type="text",label="Caption - 2")
 examples = [f"example{i}.png" for i in range(1,4)]
 
 description= "Image caption Generator"
@@ -35,7 +72,7 @@ interface = gr.Interface(
         fn=predict,
         inputs = input,
         theme="grass",
-        outputs=output,
+        outputs = [output_1,output_2],
         examples = examples,
         title=title,
         description=description,