Duplicate from jayyd/fashion-collect

Co-authored-by: Darshan J <jayyd@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Fashion Aggregator
+emoji: 👕
+colorFrom: purple
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.9
+app_file: app.py
+pinned: false
+duplicated_from: jayyd/fashion-collect
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,216 @@
+"""Provide a text query describing what you are looking for and get back out images 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?
+FAVICON = APP_DIR / "t-shirt_1f455.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"
+
+    # build a basic browser interface to a Python function
+    frontend = gr.Interface(
+        fn=fn,  # which Python function are we interacting with?
+        outputs=gr.Gallery(label="Relevant Items"),
+        # what input widgets does it need? we configure an image widget
+        inputs=gr.components.Textbox(label="Item Description"),
+        title="📝 Text2Image 👕",  # what should we display at the top of the page?
+        thumbnail=FAVICON,  # what should we display when the link is shared, e.g. on social media?
+        description=__doc__,  # what should we display just above the interface?
+        cache_examples=False,  # should we cache those inputs for faster inference? slows down start
+        allow_flagging=allow_flagging,  # should we show users the option to "flag" outputs?
+        flagging_options=["incorrect", "offensive", "other"],  # what options do users have for feedback?
+    )
+    return frontend
+
+
+class PredictorBackend:
+    """Interface to a backend that serves predictions.
+
+    To communicate with a backend accessible via a URL, provide the url kwarg.
+
+    Otherwise, runs a predictor locally.
+    """
+
+    def __init__(self, url=None):
+        if url is not None:
+            self.url = url
+            self._predict = self._predict_from_endpoint
+        else:
+            model = Retriever(image_embeddings_path=EMBEDDINGS_FILE)
+            self._predict = model.predict
+            self._search_images = model.search_images
+
+    def run(self, text: str):
+        pred, metrics = self._predict_with_metrics(text)
+        self._log_inference(pred, metrics)
+        return pred
+
+    def _predict_with_metrics(self, text: str) -> Tuple[List[str], Dict[str, float]]:
+        paths_and_scores = self._search_images(text)
+        metrics = {"mean_score": sum(paths_and_scores["score"]) / len(paths_and_scores["score"])}
+        return paths_and_scores["path"], metrics
+
+    def _log_inference(self, pred, metrics):
+        for key, value in metrics.items():
+            logging.info(f"METRIC {key} {value}")
+        logging.info(f"PRED >begin\n{pred}\nPRED >end")
+
+
+def _make_parser():
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument(
+        "--model_url",
+        default=None,
+        type=str,
+        help="Identifies a URL to which to send image data. Data is base64-encoded, converted to a utf-8 string, and then set via a POST request as JSON with the key 'image'. Default is None, which instead sends the data to a model running locally.",
+    )
+    parser.add_argument(
+        "--port",
+        default=DEFAULT_PORT,
+        type=int,
+        help=f"Port on which to expose this server. Default is {DEFAULT_PORT}.",
+    )
+    parser.add_argument(
+        "--flagging",
+        action="store_true",
+        help="Pass this flag to allow users to 'flag' model behavior and provide feedback.",
+    )
+    parser.add_argument(
+        "--gantry",
+        action="store_true",
+        help="Pass --flagging and this flag to log user feedback to Gantry. Requires GANTRY_API_KEY to be defined as an environment variable.",
+    )
+    parser.add_argument(
+        "--application",
+        default=DEFAULT_APPLICATION_NAME,
+        type=str,
+        help=f"Name of the Gantry application to which feedback should be logged, if --gantry and --flagging are passed. Default is {DEFAULT_APPLICATION_NAME}.",
+    )
+    return parser
+
+
+if __name__ == "__main__":
+    parser = _make_parser()
+    args = parser.parse_args()
+    main(args)

requirements.txt

@@ -0,0 +1,4 @@
+sentence-transformers==2.2.2
+clip @ git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1
+multilingual-clip==1.0.10
+wandb