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
Hello, only when using sift I get this error on some images:
Traceback (most recent call last):
File "server.py", line 510, in post
scores = classify_from_color_layers(colors, just_do_class=force_class_param)
File "server.py", line 219, in classify_from_color_layers
image_features = get_features(image_np)
File "server.py", line 84, in get_features
feats0 = extractor.extract(image0.to(device))
File "venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "venv\lib\site-packages\lightglue\utils.py", line 144, in extract
feats = self.forward({"image": img})
File "venv\lib\site-packages\lightglue\sift.py", line 211, in forward
p = self.extract_single_image(img)
File "venv\lib\site-packages\lightglue\sift.py", line 178, in extract_single_image
keep = filter_dog_point(
File "venv\lib\site-packages\lightglue\sift.py", line 25, in filter_dog_point
np.maximum.at(buffer, tuple(ij), s)
ValueError: array is not broadcastable to correct shape
Tried to fix it myself but I failed, pred["keypoints"] len is 0
The text was updated successfully, but these errors were encountered:
Hello, only when using sift I get this error on some images:
Tried to fix it myself but I failed, pred["keypoints"] len is 0
The text was updated successfully, but these errors were encountered: