hf_token

.gitattributes

@@ -34,4 +34,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 *.jpg filter=lfs diff=lfs merge=lfs -text
-spaces::accelerator gpu

README.md

@@ -1,30 +1,12 @@
 ---
-title: Facial Recognition App
-emoji: 🔍
-colorFrom: blue
-colorTo: purple
+title: Face Recognition
+emoji: ⚡
+colorFrom: red
+colorTo: blue
 sdk: gradio
-sdk_version: 5.29.0
+sdk_version: 5.23.0
 app_file: app.py
 pinned: false
 ---
 
-# Facial Recognition App
-
-This application uses DeepFace and Facenet for facial recognition and similarity matching.
-
-## Hardware Requirements
-- GPU: Required
-- CPU: 4+ cores recommended
-- RAM: 8GB+ recommended
-
-## Environment Setup
-The application requires the following key dependencies:
-- deepface
-- gradio
-- huggingface_hub
-- datasets
-- Pillow
-- numpy
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,176 +1,42 @@
-import os
 import numpy as np
 from PIL import Image
 import gradio as gr
 from deepface import DeepFace
-from datasets import load_dataset
-import pickle
-from io import BytesIO
-from huggingface_hub import upload_file, hf_hub_download, list_repo_files
-from pathlib import Path
-import gc
-import requests
-import time
-import shutil
-import tarfile
-import tensorflow as tf
-
-# 🔁 Limpiar almacenamiento temporal si existe
-def clean_temp_dirs():
-    print("🧹 Limpiando carpetas temporales...")
-    for folder in ["embeddings", "batches"]:
-        path = Path(folder)
-        if path.exists() and path.is_dir():
-            shutil.rmtree(path)
-            print(f"✅ Carpeta eliminada: {folder}")
-        path.mkdir(exist_ok=True)
-
-clean_temp_dirs()
-
-# 📁 Parámetros
-DATASET_ID = "Segizu/facial-recognition"
-EMBEDDINGS_SUBFOLDER = "embeddings"
-LOCAL_EMB_DIR = Path("embeddings")
-LOCAL_EMB_DIR.mkdir(exist_ok=True)
-HF_TOKEN = os.getenv("HF_TOKEN")
-headers = {"Authorization": f"Bearer {HF_TOKEN}"} if HF_TOKEN else {}
-
-# 💾 Configuración
-MAX_TEMP_STORAGE_GB = 40
-UPLOAD_EVERY = 50
+from datasets import load_dataset, DownloadConfig
+import os
+os.system("rm -rf ~/.cache/huggingface/hub/datasets--Segizu--dataset_faces")
 
-def get_folder_size(path):
-    total = 0
-    for dirpath, _, filenames in os.walk(path):
-        for f in filenames:
-            fp = os.path.join(dirpath, f)
-            total += os.path.getsize(fp)
-    return total / (1024 ** 3)
+# ✅ Cargar el dataset de Hugging Face forzando la descarga limpia
+download_config = DownloadConfig(force_download=True)
+dataset = load_dataset("Segizu/dataset_faces", download_config=download_config)
+if "train" in dataset:
+    dataset = dataset["train"]
 
-def preprocess_image(img: Image.Image) -> np.ndarray:
+# 🔄 Preprocesar imagen para Facenet
+def preprocess_image(img):
     img_rgb = img.convert("RGB")
     img_resized = img_rgb.resize((160, 160), Image.Resampling.LANCZOS)
     return np.array(img_resized)
 
-# ✅ Cargar CSV desde el dataset
-dataset = load_dataset(
-    "csv",
-    data_files="metadata.csv",
-    split="train",
-    column_names=["image"],
-    header=0
-)
-@GPU 
+# 📦 Construir base de datos de embeddings
 def build_database():
-    print(f"📊 Uso actual de almacenamiento temporal INICIO: {get_folder_size('.'):.2f} GB")
-    print("🔄 Generando embeddings...")
-    batch_size = 10
-    archive_batch_size = 50
-    batch_files = []
-    batch_index = 0
-    ARCHIVE_DIR = Path("batches")
-    ARCHIVE_DIR.mkdir(exist_ok=True)
-
-    for i in range(0, len(dataset), batch_size):
-        batch = dataset[i:i + batch_size]
-        print(f"📦 Lote {i // batch_size + 1}/{(len(dataset) + batch_size - 1) // batch_size}")
-
-        for j in range(len(batch["image"])):
-            image_url = batch["image"][j]
-
-            if not isinstance(image_url, str) or not image_url.startswith("http") or image_url.strip().lower() == "image":
-                print(f"⚠️ Saltando {i + j} - URL inválida: {image_url}")
-                continue
-
-            name = f"image_{i + j}"
-            filename = LOCAL_EMB_DIR / f"{name}.pkl"
-
-            # Verificar si ya fue subido
-            try:
-                hf_hub_download(
-                    repo_id=DATASET_ID,
-                    repo_type="dataset",
-                    filename=f"{EMBEDDINGS_SUBFOLDER}/batch_{batch_index:03}.tar.gz",
-                    token=HF_TOKEN
-                )
-                print(f"⏩ Ya existe en remoto: {name}.pkl")
-                continue
-            except:
-                pass
-
-            try:
-                response = requests.get(image_url, headers=headers, timeout=10)
-                response.raise_for_status()
-                img = Image.open(BytesIO(response.content)).convert("RGB")
-
-                img_processed = preprocess_image(img)
-                embedding = DeepFace.represent(
-                    img_path=img_processed,
-                    model_name="Facenet",
-                    enforce_detection=False
-                )[0]["embedding"]
-
-                with open(filename, "wb") as f:
-                    pickle.dump({"name": name, "img": img, "embedding": embedding}, f)
-
-                batch_files.append(filename)
-                del img_processed
-                gc.collect()
-
-                if len(batch_files) >= archive_batch_size or get_folder_size(".") > MAX_TEMP_STORAGE_GB:
-                    archive_path = ARCHIVE_DIR / f"batch_{batch_index:03}.tar.gz"
-                    with tarfile.open(archive_path, "w:gz") as tar:
-                        for file in batch_files:
-                            tar.add(file, arcname=file.name)
-
-                    print(f"📦 Empaquetado: {archive_path}")
-
-                    upload_file(
-                        path_or_fileobj=str(archive_path),
-                        path_in_repo=f"{EMBEDDINGS_SUBFOLDER}/{archive_path.name}",
-                        repo_id=DATASET_ID,
-                        repo_type="dataset",
-                        token=HF_TOKEN
-                    )
-                    print(f"✅ Subido: {archive_path.name}")
-
-                    for f in batch_files:
-                        f.unlink()
-                    archive_path.unlink()
-                    print("🧹 Limpieza completada tras subida")
-
-                    batch_files = []
-                    batch_index += 1
-                    time.sleep(2)
-                    print(f"📊 Uso actual FINAL: {get_folder_size('.'):.2f} GB")
-
-            except Exception as e:
-                print(f"❌ Error en {name}: {e}")
-                continue
-
-    if batch_files:
-        archive_path = ARCHIVE_DIR / f"batch_{batch_index:03}.tar.gz"
-        with tarfile.open(archive_path, "w:gz") as tar:
-            for file in batch_files:
-                tar.add(file, arcname=file.name)
-
-        print(f"📦 Empaquetado final: {archive_path}")
-
-        upload_file(
-            path_or_fileobj=str(archive_path),
-            path_in_repo=f"{EMBEDDINGS_SUBFOLDER}/{archive_path.name}",
-            repo_id=DATASET_ID,
-            repo_type="dataset",
-            token=HF_TOKEN
-        )
-
-        for f in batch_files:
-            f.unlink()
-        archive_path.unlink()
-        print("✅ Subida y limpieza final")
+    database = []
+    for i, item in enumerate(dataset):
+        try:
+            img = item["image"]
+            img_processed = preprocess_image(img)
+            embedding = DeepFace.represent(
+                img_path=img_processed,
+                model_name="Facenet",
+                enforce_detection=False
+            )[0]["embedding"]
+            database.append((f"image_{i}", img, embedding))
+        except Exception as e:
+            print(f"❌ No se pudo procesar imagen {i}: {e}")
+    return database
 
-# 🔍 Buscar similitudes
-def find_similar_faces(uploaded_image: Image.Image):
+# 🔍 Buscar rostros similares
+def find_similar_faces(uploaded_image):
     try:
         img_processed = preprocess_image(uploaded_image)
         query_embedding = DeepFace.represent(
@@ -178,61 +44,40 @@ def find_similar_faces(uploaded_image: Image.Image):
             model_name="Facenet",
             enforce_detection=False
         )[0]["embedding"]
-        del img_processed
-        gc.collect()
-    except Exception as e:
-        return [], f"⚠ Error procesando imagen: {str(e)}"
+    except:
+        return [], "⚠ No se detectó un rostro válido en la imagen."
 
     similarities = []
+    for name, db_img, embedding in database:
+        dist = np.linalg.norm(np.array(query_embedding) - np.array(embedding))
+        sim_score = 1 / (1 + dist)
+        similarities.append((sim_score, name, db_img))
 
-    try:
-        embedding_files = [
-            f for f in list_repo_files(DATASET_ID, repo_type="dataset", token=HF_TOKEN)
-            if f.startswith(f"{EMBEDDINGS_SUBFOLDER}/") and f.endswith(".pkl")
-        ]
-    except Exception as e:
-        return [], f"⚠ Error obteniendo archivos: {str(e)}"
+    similarities.sort(reverse=True)
+    top_matches = similarities[:]
 
-    for file_path in embedding_files:
-        try:
-            file_bytes = requests.get(
-                f"https://huggingface.co/datasets/{DATASET_ID}/resolve/main/{file_path}",
-                headers=headers,
-                timeout=10
-            ).content
-            record = pickle.loads(file_bytes)
+    gallery_items = []
+    text_summary = ""
+    for sim, name, img in top_matches:
+        caption = f"{name} - Similitud: {sim:.2f}"
+        gallery_items.append((img, caption))
+        text_summary += caption + "\n"
 
-            name = record["name"]
-            img = record["img"]
-            emb = record["embedding"]
+    return gallery_items, text_summary
 
-            dist = np.linalg.norm(np.array(query_embedding) - np.array(emb))
-            sim_score = 1 / (1 + dist)
-            similarities.append((sim_score, name, np.array(img)))
-
-        except Exception as e:
-            print(f"⚠ Error con {file_path}: {e}")
-            continue
-
-    similarities.sort(reverse=True)
-    top = similarities[:5]
-    gallery = [(img, f"{name} - Similitud: {sim:.2f}") for sim, name, img in top]
-    summary = "\n".join([f"{name} - Similitud: {sim:.2f}" for sim, name, _ in top])
-    return gallery, summary
+# ⚙️ Inicializar base
+database = build_database()
 
 # 🎛️ Interfaz Gradio
-with gr.Blocks() as demo:
-    gr.Markdown("## 🔍 Reconocimiento facial con DeepFace + ZeroGPU")
-    with gr.Row():
-        image_input = gr.Image(label="📤 Sube una imagen", type="pil")
-        find_btn = gr.Button("🔎 Buscar similares")
-    gallery = gr.Gallery(label="📸 Rostros similares")
-    summary = gr.Textbox(label="🧠 Detalle", lines=6)
-    find_btn.click(fn=find_similar_faces, inputs=image_input, outputs=[gallery, summary])
-
-    with gr.Row():
-        build_btn = gr.Button("⚙️ Construir base de embeddings (usa GPU)")
-        build_btn.click(fn=build_database, inputs=[], outputs=[])
+demo = gr.Interface(
+    fn=find_similar_faces,
+    inputs=gr.Image(label="📤 Sube una imagen", type="pil"),
+    outputs=[
+        gr.Gallery(label="📸 Rostros más similares"),
+        gr.Textbox(label="🧠 Similitud", lines=6)
+    ],
+    title="🔍 Buscador de Rostros con DeepFace",
+    description="Sube una imagen y se comparará contra los rostros del dataset alojado en Hugging Face (`Segizu/dataset_faces`)."
+)
 
 demo.launch()
-

metadata.py

@@ -1,23 +0,0 @@
-from huggingface_hub import HfApi
-import csv
-import os
-
-HF_TOKEN = os.getenv("HF_TOKEN") or ""
-repo_id = "Segizu/facial-recognition"
-
-api = HfApi()
-files = api.list_repo_files(repo_id=repo_id, repo_type="dataset", token=HF_TOKEN)
-
-# Generar URLs completas
-base_url = f"https://huggingface.co/datasets/{repo_id}/resolve/main/"
-image_urls = [base_url + f for f in files if f.lower().endswith(".jpg")]
-
-# Escribir nuevo metadata.csv
-with open("metadata.csv", "w", newline="") as f:
-    writer = csv.writer(f)
-    writer.writerow(["image"])
-    for url in image_urls:
-        writer.writerow([url])
-
-print(f"✅ metadata.csv regenerado con URLs absolutas ({len(image_urls)} imágenes)")
-

requirements.txt

@@ -1,4 +1,4 @@
-gradio==4.14.0
+gradio
 numpy
 Pillow
 opencv-python-headless
@@ -9,4 +9,3 @@ git+https://github.com/serengil/deepface.git
 # Fixes para RetinaFace
 tensorflow==2.12.0
 tf-keras
-spaces