import io import os import requests import zipfile import natsort os.environ["TOKENIZERS_PARALLELISM"] = "false" from pathlib import Path from tqdm import tqdm import streamlit as st from jax import numpy as jnp import transformers from transformers import AutoTokenizer from torchvision.transforms import Compose, CenterCrop, Normalize, Resize, ToTensor from torchvision.transforms.functional import InterpolationMode from modeling_hybrid_clip import FlaxHybridCLIP import utils @st.cache(hash_funcs={FlaxHybridCLIP: lambda _: None}) def get_model(): return FlaxHybridCLIP.from_pretrained("clip-italian/clip-italian") @st.cache(hash_funcs={transformers.models.bert.tokenization_bert_fast.BertTokenizerFast: lambda _: None}) def get_tokenizer(): return AutoTokenizer.from_pretrained("dbmdz/bert-base-italian-xxl-uncased", cache_dir="./", use_fast=True) @st.cache def download_images(): # from sentence_transformers import SentenceTransformer, util img_folder = "photos/" if not os.path.exists(img_folder) or len(os.listdir(img_folder)) == 0: os.makedirs(img_folder, exist_ok=True) photo_filename = "unsplash-25k-photos.zip" if not os.path.exists(photo_filename): # Download dataset if does not exist print(f"Downloading {photo_filename}...") response = requests.get(f"http://sbert.net/datasets/{photo_filename}", stream=True) total_size_in_bytes= int(response.headers.get('content-length', 0)) block_size = 1024 #1 Kb progress_bar = tqdm(total=total_size_in_bytes, unit='iB', unit_scale=True) for data in response.iter_content(block_size): progress_bar.update(len(data)) progress_bar.close() z = zipfile.ZipFile(io.BytesIO(response.content)) print("Extracting the dataset...") z.extractall(path=img_folder) print("Done.") @st.cache() def get_image_features(): return jnp.load("static/features/features.npy") def read_markdown_file(markdown_file): return Path(markdown_file).read_text() """ # 👋 Ciao! # CLIP Italian Demo ## HF-Flax Community Week In this demo you can search for images in the """ query = st.text_input("Insert an italian query text here...") if query: with st.spinner("Computing in progress..."): model = get_model() download_images() image_features = get_image_features() model = get_model() tokenizer = get_tokenizer() image_size = model.config.vision_config.image_size val_preprocess = Compose( [ Resize([image_size], interpolation=InterpolationMode.BICUBIC), CenterCrop(image_size), ToTensor(), Normalize( (0.48145466, 0.4578275, 0.40821073), (0.26862954, 0.26130258, 0.27577711), ), ] ) dataset = utils.CustomDataSet("photos/", transform=val_preprocess) image_paths = utils.find_image( query, model, dataset, tokenizer, image_features, n=2 ) st.image(image_paths) intro_markdown = read_markdown_file("readme.md") st.markdown(intro_markdown, unsafe_allow_html=True)