You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Can you or anyone explain me how can i change the default embedder model in this code:
from deep_sort_realtime.deepsort_tracker import DeepSort
tracker = DeepSort(max_age=5, embedder='torchreid')
bbs = object_detector.detect(frame)
tracks = tracker.update_tracks(bbs, frame=frame) # bbs expected to be a list of detections, each in tuples of ( [left,top,w,h], confidence, detection_class )
for track in tracks:
if not track.is_confirmed():
continue
track_id = track.track_id
ltrb = track.to_ltrb()
I made
embedder_model_name = "osnet_ain_x1_0"
# Inicializar o DeepSort com ReID usando TorchReID
tracker = DeepSort(max_age=5, embedder=embedder_model_name)
But i got
Traceback (most recent call last):
File "C:/Users/hemil/Desktop/v5ds380/reid.py", line 14, in <module>
tracker = DeepSort(max_age=5, embedder=embedder_model_name)
File "C:\Users\hemil\Desktop\v5ds380\venv\lib\site-packages\deep_sort_realtime\deepsort_tracker.py", line 102, in __init__
raise Exception(f"Embedder {embedder} is not a valid choice.")
Exception: Embedder osnet_ain_x1_0 is not a valid choice.
And i have this model installed
The text was updated successfully, but these errors were encountered:
The embedder argument for DeepSort is supposed to be a string chosen from 'mobilenet', 'torchreid', 'clip_RN50', 'clip_RN101', 'clip_RN50x4', 'clip_RN50x16', 'clip_ViT-B/32' and 'clip_ViT-B/16'. If you have your own embedder you wish to use you'll have to construct using DeepSort(..., embedder = None, ...) and then provide your own embeds to tracker.update_tracks().
Hi! Thanks for this great repo!
Can you or anyone explain me how can i change the default embedder model in this code:
I made
But i got
And i have this model installed
The text was updated successfully, but these errors were encountered: