File size: 1,082 Bytes
41b1911
25b37ff
fa725d5
 
25b37ff
fa725d5
 
 
f204998
fa725d5
 
a3c69ef
fa725d5
 
 
4ab173c
fa725d5
 
f204998
fa725d5
 
 
 
 
 
 
 
 
f204998
25b37ff
fa725d5
 
f204998
fa725d5
 
f204998
41b1911
fa725d5
 
f204998
 
fa725d5
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
import gradio as gr
import torch
from PIL import Image
from transformers import AutoModel, AutoTokenizer

# Load the model and tokenizer from the local path
model = AutoModel.from_pretrained('minicpm/models', trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained('minicpm/models', trust_remote_code=True)

# Set the model to evaluation mode
model.eval()

def predict(image, question):
    # Preprocess the image
    image = image.convert('RGB')

    # Create the message list
    msgs = [{'role': 'user', 'content': question}]

    # Generate a response
    res = model.chat(
        image=image,
        msgs=msgs,
        tokenizer=tokenizer,
        sampling=True,
        temperature=0.1
    )
    return res

# Create the Gradio interface
iface = gr.Interface(
    fn=predict,
    inputs=[
        gr.inputs.Image(type="pil", label="Upload an Image"),
        gr.inputs.Textbox(label="Ask a Question")
    ],
    outputs="text",
    title="Image Question Answering",
    description="Upload an image and ask a question about it."
)

# Launch the app
iface.launch()