YACWC

search_me.py

@@ -0,0 +1,92 @@
+do_load = True
+from qdrant_client import QdrantClient
+import numpy as np
+from bottle import route, run, template, request, debug
+# %%
+if do_load:
+    from lavis.models import load_model_and_preprocess, model_zoo
+    import torch
+    device = 'cpu'
+    model, vis_processors, txt_processors = load_model_and_preprocess("clip_feature_extractor", model_type="ViT-B-16", is_eval=True, device=device)
+    model.eval()
+    collection_name="nuggets_clip"
+
+# %%
+client = QdrantClient(host="localhost", grpc_port=6334, prefer_grpc=True)
+# %%
+from bottle import route, run, template
+
+@route('/get_text_match')
+def get_matches():
+    query = request.query.get('query','A large bird eating corn')
+#    averaged = request.query.get('averaged',False)
+# %%
+    max_age = request.query.get('age',5);
+# %%
+    max_age = 5
+
+    
+
+# %%
+    averaged = False
+    if isinstance(query, str):
+        averaged = bool(averaged)
+        
+    num_videos = int(request.query.get('num_videos',5))
+    print(query, num_videos, averaged)
+
+    if do_load:
+        with torch.no_grad():
+            text_input = txt_processors['eval'](query)
+            sample = {'text_input':text_input}
+            vec = model.extract_features( sample)
+            vec_search = vec.cpu().numpy().squeeze().tolist()
+    else:
+        pass
+
+
+
+    if averaged:
+        col_name=collection_name+'_averaged'
+    else:
+        col_name = collection_name
+
+    if True:
+        for i in range(num_videos, 100, 10):
+            results = client.search(collection_name = col_name,
+                            query_vector = vec_search, limit=i)
+            num_video_got = len(set([x.payload['filepath'] for x in results]))
+            if num_video_got >= num_videos:
+                break
+    else:
+        results = client.search(collection_name = col_name,
+                                query_vector = vec_search, limit=1)
+                
+  
+
+    def linux_to_win_path(form):
+        form = form.replace('/srv','file://192.168.1.242/thebears/Videos/merged/')
+        return form
+
+    def normalize_to_merged(path):
+        path = path.replace('/srv/ftp','/mergedfs/ftp')
+        path = path.replace('/mnt/archive2/videos/ftp','/mergedfs/ftp')
+        return path
+
+    resul = list()
+    for x in results:
+        pload =dict( x.payload)
+        pload['filepath'] = normalize_to_merged(pload['filepath'])
+        pload['score'] = x.score
+        pload['winpath'] = linux_to_win_path(pload['filepath'])
+        resul.append(pload)
+        
+# %%
+    return_this = {'query':query,'num_videos':num_videos,'results':resul}
+    return return_this
+
+
+
+
+debug(True)
+run(host='0.0.0.0', port=53003)

test_clip_scores.py

@@ -0,0 +1,99 @@
+print('hello')
+
+# %%
+file_path = '/srv/ftp/sidefeeder/2024/01/26/sidefeeder_01_20240126103234.mp4'
+
+from score_videos_embedding import *
+
+# %%
+score_video(file_path)
+# %%
+file_path = os.path.normpath(file_path)
+nv_vid = nv_video(file_path, 32, frame_interval=10)
+vec_path = get_vec_path(nv_vid.vid_path)
+transforms = vis_processors["eval"].transform.transforms
+all_results = list()
+if True:
+    tensor_np, frame_num = nv_vid.get_next_batch()
+    tensor = tensor_np.permute([0, 3, 1, 2]).to(torch.float32) / 255
+    tensor_pre1 = transforms[0](tensor)
+    tensor_pre2 = transforms[1](tensor_pre1)
+    tensor_mean = transforms[4](tensor_pre2)
+
+sample = {"image": tensor_mean}
+with torch.no_grad():
+    imp = model.extract_features(sample)
+    vector_to_store = imp.cpu().numpy()
+
+all_results.append([vector_to_store, frame_num])
+
+with torch.no_grad():
+    imp_text = model.extract_features(sample_text)
+# %%
+
+fwe = torch.nn.functional.cosine_similarity(imp, imp_text[3,:])
+# %%
+
+L = imp_text[-1].cpu().numpy().tolist()
+client = QdrantClient(host="localhost", grpc_port=6334, prefer_grpc=True)
+# %%
+results = client.search(collection_name = collection_name,
+                                query_vector = L, limit=1, with_vectors=True)
+
+
+results[0].payload['filepath'] == file_path
+
+vec_s = imp[frame_num.index(389)]
+vpath = get_vec_path(file_path)
+# %%
+import numpy as np
+out = np.load(vpath)
+
+out['embeds']
+idx_look = out['frame_numbers'].tolist().index(389)
+# %%
+out = score_video(file_path)
+print(np.average(np.abs(out[0][0] - imp[0].detach().cpu().numpy())))
+# %%
+from qdrant_client import QdrantClient
+client = QdrantClient(host="localhost", grpc_port=6334, prefer_grpc=True)
+# %%
+
+L = np.random.random(512).tolist()
+# %%
+from qdrant_client.models import Filter, FieldCondition, Range, MatchText
+from datetime import datetime, timedelta
+
+
+
+
+collection_name = 'nuggets_clip'
+
+query = 'hello'
+max_age = 1
+max_date = datetime.now()
+min_date = max_date - timedelta(days=max_age)
+
+
+days_step = (max_date- min_date).days
+date_arrays = list()
+for i in range(days_step):
+    date_arrays.append(min_date + timedelta(days=i))
+
+string_filter = list()
+for cand_date in date_arrays:
+    string_filter.append(cand_date.strftime('_%Y%m%d'))
+
+should_list = list()
+for str_filt in string_filter:
+    ccond  = FieldCondition(key='filepath',match=MatchText(text=str_filt))
+    should_list.append(ccond)
+# %%
+must = [FieldCondition(key="filepath",match=MatchText(text="sidefeeder")),
+        FieldCondition(key="filepath",match=MatchText(text="_20240207"))
+        ]
+
+results = client.search(collection_name = collection_name, query_vector = L, limit=10,
+                        query_filter = Filter(should=should_list))
+ 
+