fix input image size

actors_matching/api.py

@@ -3,36 +3,49 @@ import json
 import annoy
 from typing import Tuple
 
-EMBEDDING_DIMENSION=128
+EMBEDDING_DIMENSION = 128
 ANNOY_INDEX_FILE = "models/actors_annoy_index.ann"
 ANNOY_METADATA_FILE = "models/actors_annoy_metadata.json"
 ANNOY_MAPPING_FILE = "models/actors_mapping.json"
 
+
 def load_annoy_index(
-    index_file = ANNOY_INDEX_FILE, 
-    metadata_file = ANNOY_METADATA_FILE, 
-    mapping_file = ANNOY_MAPPING_FILE
+    index_file=ANNOY_INDEX_FILE,
+    metadata_file=ANNOY_METADATA_FILE,
+    mapping_file=ANNOY_MAPPING_FILE,
 ) -> Tuple[annoy.AnnoyIndex, dict]:
     """Load annoy index and associated mapping file"""
-    with open(metadata_file) as f: 
+    with open(metadata_file) as f:
         annoy_index_metadata = json.load(f)
 
     annoy_index = annoy.AnnoyIndex(f=EMBEDDING_DIMENSION, **annoy_index_metadata)
     annoy_index.load(index_file)
 
-    with open(mapping_file) as f: 
+    with open(mapping_file) as f:
         mapping = json.load(f)
         mapping = {int(k): v for k, v in mapping.items()}
     return annoy_index, mapping
 
-def analyze_image(image, annoy_index, n_matches: int = 1, num_jitters: int = 1, model: str = "large"):
+
+def analyze_image(
+    image, annoy_index, n_matches: int = 1, num_jitters: int = 1, model: str = "large"
+):
     """Extract face location, embeddings, and top n_matches matches"""
-    face_locations = face_recognition.face_locations(image)
-    embeddings = face_recognition.face_encodings(image, num_jitters=num_jitters, model=model, known_face_locations=face_locations)
+    face_locations = face_recognition.face_locations(
+        image, number_of_times_to_upsample=1
+    )
+    if not face_locations:
+        face_locations = face_recognition.face_locations(image, model="cnn")
+    embeddings = face_recognition.face_encodings(
+        image, num_jitters=num_jitters, model=model, known_face_locations=face_locations
+    )
     matches = []
     distances = []
     for emb in embeddings:
         m, d = annoy_index.get_nns_by_vector(emb, n_matches, include_distances=True)
         matches.append(m)
         distances.append(d)
-    return [dict(embeddings=e, matches=m, distances=d, face_locations=f) for e,m,d,f in zip(embeddings, matches, distances, face_locations)]
+    return [
+        dict(embeddings=e, matches=m, distances=d, face_locations=f)
+        for e, m, d, f in zip(embeddings, matches, distances, face_locations)
+    ]

app.py

@@ -59,7 +59,7 @@ iface = gr.Interface(
     and limitations of the tool!""",
     article=Path("README.md").read_text(),
     inputs=[
-        gr.inputs.Image(shape=(256, 256), label="Your image"),
+        gr.inputs.Image(shape=None, label="Your image"),
         gr.inputs.Textbox(
             label="Who's that?", placeholder="Optional, you can leave this blank"
         ),