ok

Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3.8.13
+
+WORKDIR /app
+
+COPY . /app
+
+RUN pip config set global.index-url https://pypi.mirrors.ustc.edu.cn/simple 
+RUN pip install -r requirements.txt
+
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,39 @@
+from transformers import ViltProcessor, ViltForQuestionAnswering
+from PIL import Image
+import gradio as gr
+import torch
+from gradio.themes.utils import sizes
+
+theme = gr.themes.Default(radius_size=sizes.radius_none).set(
+    block_label_text_color = '#4D63FF',
+    block_title_text_color = '#4D63FF',
+    button_primary_text_color = '#4D63FF',
+    button_primary_background_fill='#FFFFFF',
+    button_primary_border_color='#4D63FF',
+    button_primary_background_fill_hover='#EDEFFF',
+)
+processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
+model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
+
+
+def vqa(image, question):
+    inp = Image.fromarray(image.astype('uint8'), 'RGB')
+    inputs = processor(inp, question, return_tensors="pt")
+    
+    outputs = model(**inputs)
+    logits = outputs.logits
+    idx = logits.argmax(-1).item()
+
+    return model.config.id2label[idx]
+
+
+demo = gr.Interface(fn=vqa,
+                    inputs=['image', 'text'],
+                    outputs='text',
+                    title = "vqa",
+                    theme=theme,
+                    examples = [['soccer.jpg', 'how many people in the picture?']])
+
+
+if __name__ == "__main__":
+    demo.queue(concurrency_count=3).launch()

requirements.txt

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