app.py

import clip
import gc
import numpy as np
import os
import pandas as pd
import requests
import torch
import torchvision.transforms as T
import torchvision.transforms.functional as TF

#from IPython.display import display
from PIL import Image
from torch import nn
from torch.nn import functional as F
from torchvision import transforms
from torchvision.transforms.functional import InterpolationMode
from BLIP.models.blip import blip_decoder

import gradio as gr

device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
blip_image_eval_size = 384
blip_model_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model*_base_caption.pth'        
blip_model = blip_decoder(pretrained=blip_model_url, image_size=blip_image_eval_size, vit='base')
blip_model.eval()
blip_model = blip_model.to(device)

def greet(name):
    return "hi " + name + "!!"

iface = gr.Interface(fn=greet, inputs="text", outputs="text")
iface.launch()