write date

src/diary_cover_similarity.py

@@ -8,7 +8,7 @@ import faiss
 import numpy as np
 
 from utils.cache import redis_client3
-from utils.es import es_scan
+from utils.es import es_query, es_scan
 from utils.images import face_to_vec, url_to_ndarray
 
 
@@ -56,24 +56,21 @@ def save_diary_image_info(save_file, face_to_vec_f):
         }
     }
     count = 0
-    results = es_scan("diary", q)
     with open(save_file, "w") as f:
-        try:
-            for item in results:
-                diary_id = item["_id"]
-                # before_cover_url = item["_source"]["before_cover_url"] + "-w"
-                after_cover_url = item["_source"]["after_cover_url"] + "-w"
-                img = url_to_ndarray(after_cover_url)
-                if img.any():
-                    count += 1
-                    print("count: " + str(count) + " " + str(diary_id))
-                    faces = face_to_vec_f(img)
-                    for face in faces:
-                        line = str(diary_id) + "\t" + face["feature"] + "\n"
-                        # print(line)
-                        f.write(line)
-        except Exception as e:
-            print(e)
+        res_dict = es_query("diary", q, offset=2000000, size=200000)
+        for item in res_dict["hits"]["hits"]:
+            diary_id = item["_source"]["id"]
+            # before_cover_url = item["_source"]["before_cover_url"] + "-w"
+            after_cover_url = item["_source"]["after_cover_url"] + "-w"
+            img = url_to_ndarray(after_cover_url)
+            if img.any():
+                count += 1
+                print("count: " + str(count) + " " + str(diary_id))
+                faces = face_to_vec_f(img)
+                for face in faces:
+                    line = str(diary_id) + "\t" + face["feature"] + "\n"
+                    # print(line)
+                    f.write(line)
 
 
 def save_faiss_index(load_file, save_path):
@@ -174,49 +171,49 @@ def main():
     face_to_vec_f = lambda img: face_to_vec(img, face_rec, face_detector, shape_predictor)
 
     save_diary_image_info(diary_after_cover_vec_file, face_to_vec_f)
-    save_faiss_index(diary_after_cover_vec_file, faiss_index_path)
-
-    faiss_index = faiss.read_index(faiss_index_path)
-
-    imgs = [
-        "https://pic.igengmei.com/2020/07/03/1437/1b9975bb0b81-w", "https://pic.igengmei.com/2020/07/01/1812/ca64827a83da-w",
-        "https://pic.igengmei.com/2020/07/04/1711/24f4131a9b1e-w", "https://pic.igengmei.com/2020/07/04/1507/e17a995be219-w"
-    ]
-    for img_url in imgs:
-        res = get_similar_diary_ids_by_url(img_url, faiss_index, face_to_vec_f, limit=0.18232107)
-        print(res)
-
-    print("@@@@@@@@")
-    a = [
-        -0.08361373096704483, 0.06760436296463013, 0.10752949863672256, -0.020746365189552307, -0.07035162299871445,
-        -0.014547230675816536, -0.043201886117458344, -0.12196271121501923, 0.13929598033428192, -0.1360183209180832,
-        0.23247791826725006, -0.08867999166250229, -0.24177594482898712, -0.05600903555750847, -0.05371646583080292,
-        0.22015368938446045, -0.12883149087429047, -0.0822330191731453, -0.0413128100335598, 0.08704500645399094,
-        0.10081718862056732, -0.03764188289642334, 0.036720920354127884, 0.04766431450843811, -0.0685625970363617,
-        -0.38336044549942017, -0.10978807508945465, -0.07328074425458908, -0.023904308676719666, -0.007438751868903637,
-        -0.09545779973268509, 0.027364756911993027, -0.1537190079689026, -0.04008519649505615, -0.03581209108233452,
-        0.04322449117898941, -0.05686069279909134, -0.11610691249370575, 0.1640746295452118, -0.004643512889742851,
-        -0.34821364283561707, 0.03711444139480591, -0.0026186704635620117, 0.1917344480752945, 0.14298999309539795,
-        0.04084448516368866, 0.06119539216160774, -0.12611950933933258, 0.10941470414400101, -0.20786598324775696,
-        0.03435457497835159, 0.11412393301725388, 0.0602775476872921, 0.054409340023994446, -0.002967053558677435,
-        -0.12524624168872833, 0.026284342631697655, 0.08236880600452423, -0.10654348134994507, 0.00403654295951128,
-        0.10716681182384491, -0.08270247280597687, 0.018992319703102112, -0.11595900356769562, 0.18344789743423462,
-        0.0895184576511383, -0.1307670772075653, -0.15750591456890106, 0.11103398352861404, -0.13521818816661835,
-        -0.03199139982461929, 0.11129119992256165, -0.17407448589801788, -0.20658859610557556, -0.3114454746246338,
-        0.01914297416806221, 0.39955294132232666, 0.12365783005952835, -0.14545315504074097, -0.03254598751664162,
-        -0.10342024266719818, 0.03375910595059395, 0.11272192746400833, 0.21788232028484344, 0.08588762581348419,
-        0.012640122324228287, -0.07646650820970535, -0.043292030692100525, 0.21306097507476807, -0.12407292425632477,
-        -0.025112995877861977, 0.2634827196598053, 0.005047444254159927, 0.06562616676092148, -0.07397496700286865,
-        0.06206338107585907, -0.0634055882692337, 0.05882266163825989, -0.05909111723303795, 0.027562778443098068,
-        0.043835900723934174, 0.00407575536519289, -0.007656056433916092, 0.1048622876405716, -0.17822585999965668,
-        0.1303984671831131, -0.021631652489304543, 0.0836174339056015, 0.11956407874822617, 0.007379574701189995,
-        -0.07777556777000427, -0.08474794030189514, 0.09585978090763092, -0.21120299398899078, 0.1435444951057434,
-        0.19884724915027618, 0.07154559344053268, 0.06259742379188538, 0.10118959099054337, 0.10188969224691391,
-        -0.015351934358477592, -0.04335442930459976, -0.26258283853530884, -0.021509556099772453, 0.12185295671224594,
-        -0.011788002215325832, 0.01337978895753622, -0.008025042712688446
-    ]
-    res = get_similar_diary_ids_by_face_features(a, faiss_index, face_to_vec_f)
-    print(res)
+    # save_faiss_index(diary_after_cover_vec_file, faiss_index_path)
+
+    # faiss_index = faiss.read_index(faiss_index_path)
+
+    # imgs = [
+    #     "https://pic.igengmei.com/2020/07/03/1437/1b9975bb0b81-w", "https://pic.igengmei.com/2020/07/01/1812/ca64827a83da-w",
+    #     "https://pic.igengmei.com/2020/07/04/1711/24f4131a9b1e-w", "https://pic.igengmei.com/2020/07/04/1507/e17a995be219-w"
+    # ]
+    # for img_url in imgs:
+    #     res = get_similar_diary_ids_by_url(img_url, faiss_index, face_to_vec_f, limit=0.18232107)
+    #     print(res)
+
+    # print("@@@@@@@@")
+    # a = [
+    #     -0.08361373096704483, 0.06760436296463013, 0.10752949863672256, -0.020746365189552307, -0.07035162299871445,
+    #     -0.014547230675816536, -0.043201886117458344, -0.12196271121501923, 0.13929598033428192, -0.1360183209180832,
+    #     0.23247791826725006, -0.08867999166250229, -0.24177594482898712, -0.05600903555750847, -0.05371646583080292,
+    #     0.22015368938446045, -0.12883149087429047, -0.0822330191731453, -0.0413128100335598, 0.08704500645399094,
+    #     0.10081718862056732, -0.03764188289642334, 0.036720920354127884, 0.04766431450843811, -0.0685625970363617,
+    #     -0.38336044549942017, -0.10978807508945465, -0.07328074425458908, -0.023904308676719666, -0.007438751868903637,
+    #     -0.09545779973268509, 0.027364756911993027, -0.1537190079689026, -0.04008519649505615, -0.03581209108233452,
+    #     0.04322449117898941, -0.05686069279909134, -0.11610691249370575, 0.1640746295452118, -0.004643512889742851,
+    #     -0.34821364283561707, 0.03711444139480591, -0.0026186704635620117, 0.1917344480752945, 0.14298999309539795,
+    #     0.04084448516368866, 0.06119539216160774, -0.12611950933933258, 0.10941470414400101, -0.20786598324775696,
+    #     0.03435457497835159, 0.11412393301725388, 0.0602775476872921, 0.054409340023994446, -0.002967053558677435,
+    #     -0.12524624168872833, 0.026284342631697655, 0.08236880600452423, -0.10654348134994507, 0.00403654295951128,
+    #     0.10716681182384491, -0.08270247280597687, 0.018992319703102112, -0.11595900356769562, 0.18344789743423462,
+    #     0.0895184576511383, -0.1307670772075653, -0.15750591456890106, 0.11103398352861404, -0.13521818816661835,
+    #     -0.03199139982461929, 0.11129119992256165, -0.17407448589801788, -0.20658859610557556, -0.3114454746246338,
+    #     0.01914297416806221, 0.39955294132232666, 0.12365783005952835, -0.14545315504074097, -0.03254598751664162,
+    #     -0.10342024266719818, 0.03375910595059395, 0.11272192746400833, 0.21788232028484344, 0.08588762581348419,
+    #     0.012640122324228287, -0.07646650820970535, -0.043292030692100525, 0.21306097507476807, -0.12407292425632477,
+    #     -0.025112995877861977, 0.2634827196598053, 0.005047444254159927, 0.06562616676092148, -0.07397496700286865,
+    #     0.06206338107585907, -0.0634055882692337, 0.05882266163825989, -0.05909111723303795, 0.027562778443098068,
+    #     0.043835900723934174, 0.00407575536519289, -0.007656056433916092, 0.1048622876405716, -0.17822585999965668,
+    #     0.1303984671831131, -0.021631652489304543, 0.0836174339056015, 0.11956407874822617, 0.007379574701189995,
+    #     -0.07777556777000427, -0.08474794030189514, 0.09585978090763092, -0.21120299398899078, 0.1435444951057434,
+    #     0.19884724915027618, 0.07154559344053268, 0.06259742379188538, 0.10118959099054337, 0.10188969224691391,
+    #     -0.015351934358477592, -0.04335442930459976, -0.26258283853530884, -0.021509556099772453, 0.12185295671224594,
+    #     -0.011788002215325832, 0.01337978895753622, -0.008025042712688446
+    # ]
+    # res = get_similar_diary_ids_by_face_features(a, faiss_index, face_to_vec_f)
+    # print(res)
 
     # # save_diary_similarity(diary_after_cover_vec_file, faiss_index, face_to_vec_f)