Spaces:
Build error
Build error
funcionando con DEeepface
Browse files- .gitignore +13 -0
- app.py +151 -30
- requirements.txt +6 -4
.gitignore
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
.env
|
2 |
+
.venv
|
3 |
+
.env.local
|
4 |
+
.env.development.local
|
5 |
+
.env.test.local
|
6 |
+
.env.production.local
|
7 |
+
|
8 |
+
/venv
|
9 |
+
/embeddings
|
10 |
+
/batches
|
11 |
+
/metadata.csv
|
12 |
+
/metadata.csv.gz
|
13 |
+
/metadata.csv.gz.part
|
app.py
CHANGED
@@ -15,6 +15,29 @@ import shutil
|
|
15 |
import tarfile
|
16 |
import tensorflow as tf
|
17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
# 🔁 Limpiar almacenamiento temporal si existe
|
19 |
def clean_temp_dirs():
|
20 |
print("🧹 Limpiando carpetas temporales...")
|
@@ -28,7 +51,7 @@ def clean_temp_dirs():
|
|
28 |
clean_temp_dirs()
|
29 |
|
30 |
# 📁 Parámetros
|
31 |
-
DATASET_ID = "Segizu/facial-recognition"
|
32 |
EMBEDDINGS_SUBFOLDER = "embeddings"
|
33 |
LOCAL_EMB_DIR = Path("embeddings")
|
34 |
LOCAL_EMB_DIR.mkdir(exist_ok=True)
|
@@ -48,8 +71,47 @@ def get_folder_size(path):
|
|
48 |
return total / (1024 ** 3)
|
49 |
|
50 |
def preprocess_image(img: Image.Image) -> np.ndarray:
|
51 |
-
|
52 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
return np.array(img_resized)
|
54 |
|
55 |
# ✅ Cargar CSV desde el dataset
|
@@ -60,7 +122,6 @@ dataset = load_dataset(
|
|
60 |
column_names=["image"],
|
61 |
header=0
|
62 |
)
|
63 |
-
@GPU
|
64 |
def build_database():
|
65 |
print(f"📊 Uso actual de almacenamiento temporal INICIO: {get_folder_size('.'):.2f} GB")
|
66 |
print("🔄 Generando embeddings...")
|
@@ -171,49 +232,109 @@ def build_database():
|
|
171 |
|
172 |
# 🔍 Buscar similitudes
|
173 |
def find_similar_faces(uploaded_image: Image.Image):
|
|
|
|
|
|
|
174 |
try:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
175 |
img_processed = preprocess_image(uploaded_image)
|
176 |
-
|
177 |
-
|
178 |
-
|
179 |
-
|
180 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
181 |
del img_processed
|
182 |
gc.collect()
|
|
|
183 |
except Exception as e:
|
|
|
184 |
return [], f"⚠ Error procesando imagen: {str(e)}"
|
185 |
|
186 |
similarities = []
|
|
|
187 |
|
188 |
try:
|
189 |
embedding_files = [
|
190 |
f for f in list_repo_files(DATASET_ID, repo_type="dataset", token=HF_TOKEN)
|
191 |
-
if f.startswith(f"{EMBEDDINGS_SUBFOLDER}/") and f.endswith(".
|
192 |
]
|
|
|
193 |
except Exception as e:
|
|
|
194 |
return [], f"⚠ Error obteniendo archivos: {str(e)}"
|
195 |
|
196 |
-
|
197 |
-
|
198 |
-
|
199 |
-
|
200 |
-
|
201 |
-
|
202 |
-
|
203 |
-
|
204 |
-
|
205 |
-
|
206 |
-
|
207 |
-
|
208 |
-
|
209 |
-
|
210 |
-
|
211 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
212 |
|
213 |
-
|
214 |
-
|
215 |
-
continue
|
216 |
|
|
|
217 |
similarities.sort(reverse=True)
|
218 |
top = similarities[:5]
|
219 |
gallery = [(img, f"{name} - Similitud: {sim:.2f}") for sim, name, img in top]
|
@@ -234,5 +355,5 @@ with gr.Blocks() as demo:
|
|
234 |
build_btn = gr.Button("⚙️ Construir base de embeddings (usa GPU)")
|
235 |
build_btn.click(fn=build_database, inputs=[], outputs=[])
|
236 |
|
237 |
-
demo.launch()
|
238 |
|
|
|
15 |
import tarfile
|
16 |
import tensorflow as tf
|
17 |
|
18 |
+
# Configuración de GPU
|
19 |
+
print("Dispositivos GPU disponibles:", tf.config.list_physical_devices('GPU'))
|
20 |
+
|
21 |
+
# Configurar memoria GPU
|
22 |
+
gpus = tf.config.list_physical_devices('GPU')
|
23 |
+
if gpus:
|
24 |
+
try:
|
25 |
+
# Permitir crecimiento de memoria
|
26 |
+
for gpu in gpus:
|
27 |
+
tf.config.experimental.set_memory_growth(gpu, True)
|
28 |
+
print("✅ GPU configurada correctamente")
|
29 |
+
|
30 |
+
# Configurar para usar solo GPU
|
31 |
+
tf.config.set_visible_devices(gpus[0], 'GPU')
|
32 |
+
print(f"✅ Usando GPU: {gpus[0]}")
|
33 |
+
except RuntimeError as e:
|
34 |
+
print(f"⚠️ Error configurando GPU: {e}")
|
35 |
+
else:
|
36 |
+
print("⚠️ No se detectó GPU, usando CPU")
|
37 |
+
|
38 |
+
# Configurar para usar mixed precision
|
39 |
+
tf.keras.mixed_precision.set_global_policy('mixed_float16')
|
40 |
+
|
41 |
# 🔁 Limpiar almacenamiento temporal si existe
|
42 |
def clean_temp_dirs():
|
43 |
print("🧹 Limpiando carpetas temporales...")
|
|
|
51 |
clean_temp_dirs()
|
52 |
|
53 |
# 📁 Parámetros
|
54 |
+
DATASET_ID = "Segizu/facial-recognition-preview"
|
55 |
EMBEDDINGS_SUBFOLDER = "embeddings"
|
56 |
LOCAL_EMB_DIR = Path("embeddings")
|
57 |
LOCAL_EMB_DIR.mkdir(exist_ok=True)
|
|
|
71 |
return total / (1024 ** 3)
|
72 |
|
73 |
def preprocess_image(img: Image.Image) -> np.ndarray:
|
74 |
+
# Convertir a RGB si no lo es
|
75 |
+
if img.mode != 'RGB':
|
76 |
+
img = img.convert('RGB')
|
77 |
+
|
78 |
+
# Obtener la orientación EXIF si existe
|
79 |
+
try:
|
80 |
+
exif = img._getexif()
|
81 |
+
if exif is not None:
|
82 |
+
orientation = exif.get(274) # 274 es el tag de orientación en EXIF
|
83 |
+
if orientation is not None:
|
84 |
+
# Rotar la imagen según la orientación EXIF
|
85 |
+
if orientation == 3:
|
86 |
+
img = img.rotate(180, expand=True)
|
87 |
+
elif orientation == 6:
|
88 |
+
img = img.rotate(270, expand=True)
|
89 |
+
elif orientation == 8:
|
90 |
+
img = img.rotate(90, expand=True)
|
91 |
+
except:
|
92 |
+
pass # Si no hay EXIF o hay error, continuamos con la imagen original
|
93 |
+
|
94 |
+
# Intentar detectar la orientación del rostro
|
95 |
+
try:
|
96 |
+
# Convertir a array numpy para DeepFace
|
97 |
+
img_array = np.array(img)
|
98 |
+
# Detectar rostros con GPU
|
99 |
+
face_objs = DeepFace.extract_faces(
|
100 |
+
img_path=img_array,
|
101 |
+
target_size=(160, 160),
|
102 |
+
detector_backend='retinaface',
|
103 |
+
enforce_detection=False
|
104 |
+
)
|
105 |
+
|
106 |
+
if face_objs and len(face_objs) > 0:
|
107 |
+
# Si se detecta un rostro, usar la imagen detectada
|
108 |
+
img_array = face_objs[0]['face']
|
109 |
+
return img_array
|
110 |
+
except:
|
111 |
+
pass # Si falla la detección, continuamos con el procesamiento normal
|
112 |
+
|
113 |
+
# Si no se detectó rostro o falló la detección, redimensionar la imagen original
|
114 |
+
img_resized = img.resize((160, 160), Image.Resampling.LANCZOS)
|
115 |
return np.array(img_resized)
|
116 |
|
117 |
# ✅ Cargar CSV desde el dataset
|
|
|
122 |
column_names=["image"],
|
123 |
header=0
|
124 |
)
|
|
|
125 |
def build_database():
|
126 |
print(f"📊 Uso actual de almacenamiento temporal INICIO: {get_folder_size('.'):.2f} GB")
|
127 |
print("🔄 Generando embeddings...")
|
|
|
232 |
|
233 |
# 🔍 Buscar similitudes
|
234 |
def find_similar_faces(uploaded_image: Image.Image):
|
235 |
+
if uploaded_image is None:
|
236 |
+
return [], "⚠ Por favor, sube una imagen primero"
|
237 |
+
|
238 |
try:
|
239 |
+
print("🔄 Procesando imagen de entrada...")
|
240 |
+
# Convertir a RGB si no lo es
|
241 |
+
if uploaded_image.mode != 'RGB':
|
242 |
+
uploaded_image = uploaded_image.convert('RGB')
|
243 |
+
|
244 |
+
# Mostrar dimensiones de la imagen
|
245 |
+
print(f"📐 Dimensiones de la imagen: {uploaded_image.size}")
|
246 |
+
|
247 |
img_processed = preprocess_image(uploaded_image)
|
248 |
+
print("✅ Imagen preprocesada correctamente")
|
249 |
+
|
250 |
+
# Intentar primero con enforce_detection=True
|
251 |
+
try:
|
252 |
+
query_embedding = DeepFace.represent(
|
253 |
+
img_path=img_processed,
|
254 |
+
model_name="Facenet",
|
255 |
+
enforce_detection=True,
|
256 |
+
detector_backend='retinaface'
|
257 |
+
)[0]["embedding"]
|
258 |
+
print("✅ Rostro detectado con enforce_detection=True")
|
259 |
+
except Exception as e:
|
260 |
+
print(f"⚠ No se pudo detectar rostro con enforce_detection=True, intentando con False: {str(e)}")
|
261 |
+
# Si falla, intentar con enforce_detection=False
|
262 |
+
query_embedding = DeepFace.represent(
|
263 |
+
img_path=img_processed,
|
264 |
+
model_name="Facenet",
|
265 |
+
enforce_detection=False,
|
266 |
+
detector_backend='retinaface'
|
267 |
+
)[0]["embedding"]
|
268 |
+
print("✅ Embedding generado con enforce_detection=False")
|
269 |
+
|
270 |
del img_processed
|
271 |
gc.collect()
|
272 |
+
|
273 |
except Exception as e:
|
274 |
+
print(f"❌ Error en procesamiento de imagen: {str(e)}")
|
275 |
return [], f"⚠ Error procesando imagen: {str(e)}"
|
276 |
|
277 |
similarities = []
|
278 |
+
print("🔍 Buscando similitudes en la base de datos...")
|
279 |
|
280 |
try:
|
281 |
embedding_files = [
|
282 |
f for f in list_repo_files(DATASET_ID, repo_type="dataset", token=HF_TOKEN)
|
283 |
+
if f.startswith(f"{EMBEDDINGS_SUBFOLDER}/") and f.endswith(".tar.gz")
|
284 |
]
|
285 |
+
print(f"📁 Encontrados {len(embedding_files)} archivos de embeddings")
|
286 |
except Exception as e:
|
287 |
+
print(f"❌ Error obteniendo archivos: {str(e)}")
|
288 |
return [], f"⚠ Error obteniendo archivos: {str(e)}"
|
289 |
|
290 |
+
# Procesar en lotes para mejor rendimiento
|
291 |
+
batch_size = 10
|
292 |
+
for i in range(0, len(embedding_files), batch_size):
|
293 |
+
batch_files = embedding_files[i:i + batch_size]
|
294 |
+
print(f"📦 Procesando lote {i//batch_size + 1}/{(len(embedding_files) + batch_size - 1)//batch_size}")
|
295 |
+
|
296 |
+
for file_path in batch_files:
|
297 |
+
try:
|
298 |
+
file_bytes = requests.get(
|
299 |
+
f"https://huggingface.co/datasets/{DATASET_ID}/resolve/main/{file_path}",
|
300 |
+
headers=headers,
|
301 |
+
timeout=30
|
302 |
+
).content
|
303 |
+
|
304 |
+
# Crear un archivo temporal para el tar.gz
|
305 |
+
temp_archive = Path("temp_archive.tar.gz")
|
306 |
+
with open(temp_archive, "wb") as f:
|
307 |
+
f.write(file_bytes)
|
308 |
+
|
309 |
+
# Extraer el contenido
|
310 |
+
with tarfile.open(temp_archive, "r:gz") as tar:
|
311 |
+
tar.extractall(path="temp_extract")
|
312 |
+
|
313 |
+
# Procesar cada archivo .pkl en el tar
|
314 |
+
for pkl_file in Path("temp_extract").glob("*.pkl"):
|
315 |
+
with open(pkl_file, "rb") as f:
|
316 |
+
record = pickle.load(f)
|
317 |
+
|
318 |
+
name = record["name"]
|
319 |
+
img = record["img"]
|
320 |
+
emb = record["embedding"]
|
321 |
+
|
322 |
+
dist = np.linalg.norm(np.array(query_embedding) - np.array(emb))
|
323 |
+
sim_score = 1 / (1 + dist)
|
324 |
+
similarities.append((sim_score, name, np.array(img)))
|
325 |
+
|
326 |
+
# Limpiar archivos temporales
|
327 |
+
shutil.rmtree("temp_extract")
|
328 |
+
temp_archive.unlink()
|
329 |
+
|
330 |
+
except Exception as e:
|
331 |
+
print(f"⚠ Error procesando {file_path}: {e}")
|
332 |
+
continue
|
333 |
|
334 |
+
if not similarities:
|
335 |
+
return [], "⚠ No se encontraron similitudes en la base de datos"
|
|
|
336 |
|
337 |
+
print(f"✅ Encontradas {len(similarities)} similitudes")
|
338 |
similarities.sort(reverse=True)
|
339 |
top = similarities[:5]
|
340 |
gallery = [(img, f"{name} - Similitud: {sim:.2f}") for sim, name, img in top]
|
|
|
355 |
build_btn = gr.Button("⚙️ Construir base de embeddings (usa GPU)")
|
356 |
build_btn.click(fn=build_database, inputs=[], outputs=[])
|
357 |
|
358 |
+
demo.launch(share=True)
|
359 |
|
requirements.txt
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
gradio==
|
2 |
numpy
|
3 |
Pillow
|
4 |
opencv-python-headless
|
@@ -6,7 +6,9 @@ opencv-python-headless
|
|
6 |
# DeepFace desde GitHub
|
7 |
git+https://github.com/serengil/deepface.git
|
8 |
|
9 |
-
#
|
10 |
-
tensorflow==2.
|
11 |
tf-keras
|
12 |
-
spaces
|
|
|
|
|
|
1 |
+
gradio==3.50.2
|
2 |
numpy
|
3 |
Pillow
|
4 |
opencv-python-headless
|
|
|
6 |
# DeepFace desde GitHub
|
7 |
git+https://github.com/serengil/deepface.git
|
8 |
|
9 |
+
# TensorFlow con soporte GPU
|
10 |
+
tensorflow-gpu==2.15.0
|
11 |
tf-keras
|
12 |
+
spaces
|
13 |
+
datasets
|
14 |
+
pydantic>=2.0.0,<3.0.0
|