Spaces:
Sleeping
Sleeping
File size: 1,757 Bytes
1e1a418 96072ff 37bed6c 1e1a418 37bed6c 1e1a418 96072ff 1e1a418 37bed6c |
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 45 46 47 48 49 50 51 52 53 54 55 |
import torch
import re
from PIL import Image
import requests
import streamlit as st
from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel
st.set_page_config(page_title="Captionize")
st.title("🤖 Captionize")
st.subheader("Generate Captions for your Image...")
st.sidebar.image('./csv_analysis.png',width=300, use_column_width=True)
# Applying Styling
st.markdown("""
<style>
div.stButton > button:first-child {
background-color: #0099ff;
color:#ffffff;
}
div.stButton > button:hover {
background-color: #00ff00;
color:#FFFFFF;
}
</style>""", unsafe_allow_html=True)
device='cpu'
encoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
decoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
model_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
feature_extractor = ViTFeatureExtractor.from_pretrained(encoder_checkpoint)
tokenizer = AutoTokenizer.from_pretrained(decoder_checkpoint)
model = VisionEncoderDecoderModel.from_pretrained(model_checkpoint).to(device)
def predict(image,max_length=64, num_beams=4):
#image = image.convert('RGB')
image = Image.open(requests.get(image, stream=True).raw).convert("RGB")
image = feature_extractor(image, return_tensors="pt").pixel_values.to(device)
clean_text = lambda x: x.replace('<|endoftext|>','').split('\n')[0]
caption_ids = model.generate(image, max_length = max_length)[0]
caption_text = clean_text(tokenizer.decode(caption_ids))
return caption_text
pic = st.file_uploader(label="Please upload any Image here 😎",type=['png', 'jpeg', 'jpg'], help="Only 'png', 'jpeg' or 'jpg' formats allowed")
button = st.button("Generate Caption")
if button:
# Get Response
caption = predict(pic)
st.write(caption) |