prismer / app.py
shikunl's picture
Fix ocr
19327c9
raw
history blame
1.56 kB
#!/usr/bin/env python
from __future__ import annotations
import os
import shutil
import subprocess
import gradio as gr
if os.getenv('SYSTEM') == 'spaces':
with open('patch') as f:
subprocess.run('patch -p1'.split(), cwd='prismer', stdin=f)
shutil.copytree('prismer/helpers/images',
'prismer/images',
dirs_exist_ok=True)
from app_caption import create_demo as create_demo_caption
from app_vqa import create_demo as create_demo_vqa
from prismer_model import build_deformable_conv, download_models
# Prepare model checkpoints
download_models()
build_deformable_conv()
# Demo file here
description = """
# Prismer
The official demo for **Prismer: A Vision-Language Model with An Ensemble of Experts**.
Please refer to our [project page](https://shikun.io/projects/prismer) or [github](https://github.com/NVlabs/prismer) for more details.
"""
if (SPACE_ID := os.getenv('SPACE_ID')) is not None:
description += f'For faster inference without waiting in queue, you may duplicate the space and upgrade to GPU in settings. <a href="https://huggingface.co/spaces/{SPACE_ID}?duplicate=true"><img style="display: inline; margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space" /></a>'
with gr.Blocks() as demo:
gr.Markdown(description)
with gr.Tabs():
with gr.TabItem('Zero-shot Image Captioning'):
create_demo_caption()
with gr.TabItem('Visual Question Answering'):
create_demo_vqa()
demo.queue(api_open=False).launch()