"""Find your apparel effortlessly. Just describe your apparel and get the relevant recommendations with links!""" import argparse import logging import os import wandb import gradio as gr import zipfile import pickle from pathlib import Path from typing import List, Any, Dict from PIL import Image from pathlib import Path from transformers import AutoTokenizer from sentence_transformers import SentenceTransformer, util from multilingual_clip import pt_multilingual_clip import torch from pathlib import Path from typing import Callable, Dict, List, Tuple from PIL.Image import Image print(__file__) os.environ["CUDA_VISIBLE_DEVICES"] = "" # do not use GPU logging.basicConfig(level=logging.INFO) DEFAULT_APPLICATION_NAME = "fashion-aggregator" APP_DIR = Path(__file__).resolve().parent # what is the directory for this application? LOGO = APP_DIR / "1001epochs.png" # path to a small image for display in browser tab and social media README = APP_DIR / "README.md" # path to an app readme file in HTML/markdown DEFAULT_PORT = 11700 EMBEDDINGS_DIR = "artifacts/img-embeddings" EMBEDDINGS_FILE = os.path.join(EMBEDDINGS_DIR, "embeddings.pkl") RAW_PHOTOS_DIR = "artifacts/raw-photos" # Download image embeddings and raw photos wandb.login(key="4b5a23a662b20fdd61f2aeb5032cf56fdce278a4") # os.getenv('wandb') api = wandb.Api() artifact_embeddings = api.artifact("ryparmar/fashion-aggregator/unimoda-images:v1") artifact_embeddings.download(EMBEDDINGS_DIR) artifact_raw_photos = api.artifact("ryparmar/fashion-aggregator/unimoda-raw-images:v1") artifact_raw_photos.download("artifacts") with zipfile.ZipFile("artifacts/unimoda.zip", 'r') as zip_ref: zip_ref.extractall(RAW_PHOTOS_DIR) class TextEncoder: """Encodes the given text""" def __init__(self, model_path="M-CLIP/XLM-Roberta-Large-Vit-B-32"): self.model = pt_multilingual_clip.MultilingualCLIP.from_pretrained(model_path) self.tokenizer = AutoTokenizer.from_pretrained(model_path) @torch.no_grad() def encode(self, query: str) -> torch.Tensor: """Predict/infer text embedding for a given query.""" query_emb = self.model.forward([query], self.tokenizer) return query_emb class ImageEnoder: """Encodes the given image""" def __init__(self, model_path="clip-ViT-B-32"): self.model = SentenceTransformer(model_path) @torch.no_grad() def encode(self, image: Image) -> torch.Tensor: """Predict/infer text embedding for a given query.""" image_emb = self.model.encode([image], convert_to_tensor=True, show_progress_bar=False) return image_emb class Retriever: """Retrieves relevant images for a given text embedding.""" def __init__(self, image_embeddings_path=None): self.text_encoder = TextEncoder() self.image_encoder = ImageEnoder() with open(image_embeddings_path, "rb") as file: self.image_names, self.image_embeddings = pickle.load(file) self.image_names = [ img_name.replace("fashion-aggregator/fashion_aggregator/data/photos/", "") for img_name in self.image_names ] print("Images:", len(self.image_names)) @torch.no_grad() def predict(self, text_query: str, k: int = 10) -> List[Any]: """Return top-k relevant items for a given embedding""" query_emb = self.text_encoder.encode(text_query) relevant_images = util.semantic_search(query_emb, self.image_embeddings, top_k=k)[0] return relevant_images @torch.no_grad() def search_images(self, text_query: str, k: int = 6) -> Dict[str, List[Any]]: """Return top-k relevant images for a given embedding""" images = self.predict(text_query, k) paths_and_scores = {"path": [], "score": []} for img in images: paths_and_scores["path"].append(os.path.join(RAW_PHOTOS_DIR, self.image_names[img["corpus_id"]])) paths_and_scores["score"].append(img["score"]) return paths_and_scores def main(args): predictor = PredictorBackend(url=args.model_url) frontend = make_frontend(predictor.run, flagging=args.flagging, gantry=args.gantry, app_name=args.application) frontend.launch( # server_name="0.0.0.0", # make server accessible, binding all interfaces # noqa: S104 # server_port=args.port, # set a port to bind to, failing if unavailable # share=False, # should we create a (temporary) public link on https://gradio.app? # favicon_path=FAVICON, # what icon should we display in the address bar? ) def make_frontend( fn: Callable[[Image], str], flagging: bool = False, gantry: bool = False, app_name: str = "fashion-aggregator" ): """Creates a gradio.Interface frontend for text to image search function.""" allow_flagging = "never" # Create a Blocks interface frontend = gr.Interface( fn=fn, inputs=gr.inputs.Textbox(label="Item Description", placeholder="Enter item description here"), outputs=gr.outputs.Gallery(label="Relevant Items", show_labels=True, label_position="below"), title="Fashion Aggregator".format(logo=LOGO), thumbnail=FAVICON, description="Discover your perfect apparel effortlessly. Simply describe what you're looking for!", cache_examples=False, allow_flagging=allow_flagging, flagging_options=["incorrect", "offensive", "other"], ) # Customize the HTML template to include the disclaimer and style the title frontend.template = """
{{interface_html}}