Please add some kind of documentation. Maybe even the files you have in the gitignore :)
But nevertheless thanks alot! :)

Hi, @SamL98

I got a little confused about the Line 43 in keypoints.py, it wrote offset = -LA.inv(HD).dot(J). You defined the HD as a 3 by 3 array, and the shape of J is 1 by 3. How that possible to use a dot operation between them?

With the picture that I'm working, sigma = kp[2]*1.5 on line 50 in orientation.py returns a negative sigma value. This obviously results in an error when passed to gaussian_filter. Any idea why kp[2] might be negative?

When I feed in different images to the SIFT class to extract the SIFT features sometimes for some images I keep getting this error:
weight = kernel[oy+w, ox+w] * m
IndexError: index 9 is out of bounds for axis 1 with size 9

I would truly appreciate if you could fix this as I cannot find the root to the problem. In the case you I have a paypal link. I would gladly donate for all the amazing work you did. This SIFT implementation is a very good one :)

File PySIFT/orientation.py", line 65, in assign_orientation
weight = kernel[oy+w, ox+w] * m
IndexError: index 5 is out of bounds for axis 1 with size 5