File size: 1,674 Bytes
20dcad7 4cea813 20dcad7 d14c041 20dcad7 4cea813 d14c041 4cea813 20dcad7 |
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 56 57 58 59 60 61 62 63 64 65 66 |
import streamlit as st
import streamlit.components.v1 as components
from PIL import Image
from predict import generate_text
from model import load_clip_model, load_gpt_model, load_model
# Configure Streamlit page
st.set_page_config(page_title="Caption Machine", page_icon="💥")
# Set Session
model, image_transform, tokenizer = load_model()
if 'model' not in st.session_state:
st.session_state['model'] = model
if 'image_transform' not in st.session_state:
st.session_state['image_transform'] = image_transform
if 'tokenizer' not in st.session_state:
st.session_state['tokenizer'] = tokenizer
# Force responsive layout for columns also on mobile
st.write(
"""<style>
[data-testid="column"] {
width: calc(50% - 1rem);
flex: 1 1 calc(50% - 1rem);
min-width: calc(50% - 1rem);
}
</style>""",
unsafe_allow_html=True,
)
# Render Streamlit page
st.title("Image Captioner")
st.markdown(
"This app generates Image Caption using OpenAI's [GPT-2](https://openai.com/research/better-language-models) and [CLIP](https://openai.com/research/clip) model."
)
# st.subheader("Model Architecture")
# image = Image.open('model.png')
# st.image(image, caption=None, width=500)
upload_file = st.file_uploader("Upload an image:", type=['png','jpg','jpeg'])
# Checking the Format of the page
if upload_file is not None:
img = Image.open(upload_file)
st.image(img)
st.write("Image Uploaded Successfully")
# gpt_model, tokenizer = load_gpt_model()
caption = generate_text(st.session_state['model'], img, st.session_state['tokenizer'], st.session_state['image_transform'])
st.write(caption)
|