update model

.gradio/flagged/dataset1.csv

@@ -0,0 +1,3 @@
+image,output,timestamp
+.gradio\flagged\image\4b60174fa7b64d40f429\1984b509-acc2-47c0-8d72-5a4692938d80.jpg,,2025-04-25 16:08:27.527342
+.gradio\flagged\image\ac23ccb956d7b24e0154\1984b509-acc2-47c0-8d72-5a4692938d80.jpg,,2025-04-25 16:08:29.346974

app.py

@@ -1,7 +1,29 @@
 import gradio as gr
+from transformers import BlipProcessor, BlipForConditionalGeneration
+from PIL import Image
+import torch
 
-def greet(name):
-    return "Hello " + name + "!!"
+# Load model
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model.to(device)
+
+# Inference function
+def predict_caption(image):
+    if image.mode != "RGB":
+        image = image.convert("RGB")
+    
+    inputs = processor(images=image, return_tensors="pt").to(device)
+    output = model.generate(**inputs, max_new_tokens=20)
+    caption = processor.decode(output[0], skip_special_tokens=True)
+    return caption
+
+# Gradio UI
+demo = gr.Interface(fn=predict_caption,
+                    inputs=gr.Image(type="pil"),
+                    outputs="text",
+                    title="📸 BLIP Image Captioning",
+                    description="Tải ảnh lên và nhận mô tả tự động bằng BLIP từ Salesforce.")
 demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+torch
+gradio
+Pillow