Update app.py

app.py

@@ -1,21 +1,31 @@
-Run pip install transformers
-Run pip install gradio
+from tranformers import VisionEncoderDecoderModle, ViTImageProcer, Autotokenizer
+import torch
 from PIL import Image
-import requests
-import gradio as gr
 
-from transformers import BlipProcessor, BlipForConditionalGeneration
+model = VisionEncoderDecoderModle.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+feature_external = ViTImageProcer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+tokenizer = Autotokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
 
-model_id = "Salesforce/blip-image-captioning-base"
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
 
-model = BlipForConditionalGeneration.from_pretrained(model_id)
-processor = BlipProcessor.from_pretrained(model_id)
+max_length = 16
+num_beams = 4
+gen_kwargs = ("max_length" : max_length, "num_beams" : num_beams)
 
-def launch(input):
-    image = Image.open(requests.get(input, stream=True).raw).convert('RGB')
-    inputs = processor(image, return_tensors="pt")
-    out = model.generate(**inputs)
-    return processor.decode(out[0], skip_special_tokens=True)
+def predict_caption(image_paths):
+    images = []
+    for image_path in image_paths:
+        image = Image.open(image_path)
+        if image.mode != "RGB":
+            image = image.convert(mode="RGB")
+        images.append(image)
+
+    pixel_values = feature_extractor(images=images, return_pixel_values=True).pixel_values
+    pixel_values = pixel_values.to(device)
+
+    output_ids = model.generate(pixel_values, **gen_kwargs)
+
+    preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
+    return preds
 
-iface = gr.Interface(launch, inputs="text", outputs="text")
-iface.launch()