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
Copy file name to clipboardExpand all lines: README.md
+5-12Lines changed: 5 additions & 12 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -10,7 +10,6 @@ Check out the [documentation](https://popsift.readthedocs.io/) for more info.
10
10
11
11
## HW requirements
12
12
13
-
14
13
PopSift compiles and works with NVidia cards of compute capability >= 3.0 (including the GT 650M), but the code is developed with the compute capability 5.2 card GTX 980 Ti in mind.
15
14
16
15
CUDA SDK 11 does no longer support compute capability 3.0. 3.5 is still supported with deprecation warning.
@@ -46,15 +45,6 @@ Some build options are available:
46
45
47
46
*`BUILD_SHARED_LIBS` (default: `ON`) controls the type of library to build (`ON` for shared libraries, `OFF` for static)
The caller must create a `popart::Config` struct (documented in `src/sift/sift_conf.h`) to control the behaviour of the PopSift, and instantiate an object of class `PopSift` (found in `src/sift/popsift.h`).
@@ -111,6 +99,11 @@ PopSift can be configured at runtime to use constants that affect it behaviours.
111
99
In particular, users can choose to generate results very similar to VLFeat or results that are closer (but not as close) to the SIFT implementation of the OpenCV extras.
112
100
We acknowledge that there is at least one SIFT implementation that is vastly faster, but it makes considerable sacrifices in terms of accuracy and compatibility.
0 commit comments