Update app.py

app.py

@@ -1,22 +1,23 @@
-#from PIL import Image
-#import requests
+from PIL import Image
+import requests
 import gradio as gr
-#from io import BytesIO
+from io import BytesIO
 
-#from transformers import BlipProcessor, BlipForConditionalGeneration
+from transformers import BlipProcessor, BlipForConditionalGeneration
 
-#model_id = "Salesforce/blip-image-captioning-base"
+model_id = "Salesforce/blip-image-captioning-base"
 
-#model = BlipForConditionalGeneration.from_pretrained(model_id)
-#processor = BlipProcessor.from_pretrained(model_id)
+model = BlipForConditionalGeneration.from_pretrained(model_id)
+processor = BlipProcessor.from_pretrained(model_id)
 
-#def launch(image):
-#    #image = Image.open(BytesIO(input_image)).convert('RGB')
-#    inputs = processor(image, return_tensors="pt")
-#    out = model.generate(**inputs)
-#    return processor.decode(out[0], skip_special_tokens=True)
+def launch(image):
+    #image = Image.open(BytesIO(input_image)).convert('RGB')
+    inputsData = data.pop("inputs", data)
+    # decode base64 image to PIL
+    image = Image.open(BytesIO(base64.b64decode(inputsData["image"])))
+    inputs = processor(image, return_tensors="pt")
+    out = model.generate(**inputs)
+    return processor.decode(out[0], skip_special_tokens=True)
 
-#iface = gr.Interface(launch, inputs=gr.inputs.Image(), outputs="text")
-#iface.launch()
-
-gr.Interface.load("models/Salesforce/blip-image-captioning-base").launch()
+iface = gr.Interface(launch, inputs=gr.inputs.Image(), outputs="text")
+iface.launch()