nik-v9 / heaputil Goto Github PK

Thanks for sharing your code of your works.

I want to follow the commandline for suggested inference,
so I tried to download your data.zip through suggested MEGA link.

But it seems that there is some errors regarding the downloaded file on Ubuntu, it displays:
'data.zip': empty archive

Maybe there are some errors or expiration of your MEGA link, so it would be great if you could check it.
I 'm looking forward to your reply.

Hyeonjae Gil

First of all, Thank you for your wonderful work.

I have a question about the Berlin Kudamm datasets.

In your letter, Berlin Kudamm dataset was explained as follows.
" ... The total traverse span is about 3 Km, where the reference traverse contains 314 frames and the query traverse has 280 frames."

When i checked the more details regarding the Berlin Kudamm dataset on reference paper, I found out that there was a difference about Berlin Kudamm datasets.

In reference paper, Berlin Kudamm datasets was explained that the number of frames was 424 frames as follows.

I wonder why there is a difference. Can you explain why?

Thank you in advance.

When I run pip install -r requirements.txt I'm faced with this error.

Collecting faiss-gpu>=1.7.1
Using cached faiss-gpu-1.7.1.post2.tar.gz (40 kB)
Preparing metadata (setup.py) ... done
WARNING: Generating metadata for package faiss-gpu produced metadata for project name faiss-cpu. Fix your #egg=faiss-gpu fragments.
WARNING: Discarding https://files.pythonhosted.org/packages/17/76/47d0cc8161f4bf988583a2839bb1e56baf09d6b80cfa472b9eba4d5f543b/faiss-gpu-1.7.1.post2.tar.gz#sha256=877478752c03678fd9b9553e4ffadca82cd337bba9bb6a939aa1c6ea561a7a58 (from https://pypi.org/simple/faiss-gpu/). Requested faiss-cpu from https://files.pythonhosted.org/packages/17/76/47d0cc8161f4bf988583a2839bb1e56baf09d6b80cfa472b9eba4d5f543b/faiss-gpu-1.7.1.post2.tar.gz#sha256=877478752c03678fd9b9553e4ffadca82cd337bba9bb6a939aa1c6ea561a7a58 (from -r requirements.txt (line 5)) has inconsistent name: filename has 'faiss-gpu', but metadata has 'faiss-cpu'
Using cached faiss-gpu-1.7.1.post1.tar.gz (41 kB)
Preparing metadata (setup.py) ... done
WARNING: Generating metadata for package faiss-gpu produced metadata for project name faiss-cpu. Fix your #egg=faiss-gpu fragments.
WARNING: Discarding https://files.pythonhosted.org/packages/39/8d/b62bc92c8dd4b2a99d4a06b8804280f6445748b6d698eabb037e111080c7/faiss-gpu-1.7.1.post1.tar.gz#sha256=4e71f6ed035df0fee0eb40a35ce819c3f295116df15f513f18f40be8ac99be1f (from https://pypi.org/simple/faiss-gpu/). Requested faiss-cpu from https://files.pythonhosted.org/packages/39/8d/b62bc92c8dd4b2a99d4a06b8804280f6445748b6d698eabb037e111080c7/faiss-gpu-1.7.1.post1.tar.gz#sha256=4e71f6ed035df0fee0eb40a35ce819c3f295116df15f513f18f40be8ac99be1f (from -r requirements.txt (line 5)) has inconsistent name: filename has 'faiss-gpu', but metadata has 'faiss-cpu'
Using cached faiss-gpu-1.7.1.tar.gz (40 kB)
Preparing metadata (setup.py) ... done
WARNING: Generating metadata for package faiss-gpu produced metadata for project name faiss-cpu. Fix your #egg=faiss-gpu fragments.
WARNING: Discarding https://files.pythonhosted.org/packages/51/85/7a7490dbecaea9272953b88e236a45fe8c47571a069bc28b352f0b224ea3/faiss-gpu-1.7.1.tar.gz#sha256=78b8495efd00e5e25fd0046a652f5b4587af0aebaf006fff73ac66e9610ba9fc (from https://pypi.org/simple/faiss-gpu/). Requested faiss-cpu from https://files.pythonhosted.org/packages/51/85/7a7490dbecaea9272953b88e236a45fe8c47571a069bc28b352f0b224ea3/faiss-gpu-1.7.1.tar.gz#sha256=78b8495efd00e5e25fd0046a652f5b4587af0aebaf006fff73ac66e9610ba9fc (from -r requirements.txt (line 5)) has inconsistent name: filename has 'faiss-gpu', but metadata has 'faiss-cpu'
ERROR: Could not find a version that satisfies the requirement faiss-gpu>=1.7.1 (from versions: 1.5.3, 1.6.0, 1.6.1, 1.6.3, 1.6.4, 1.6.4.post2, 1.6.5, 1.7.0, 1.7.1, 1.7.1.post1, 1.7.1.post2)
ERROR: No matching distribution found for faiss-gpu>=1.7.1

Hello, I really appreciate the work you have done, but I have problems downloading the Oxford RobotCar dataset. Can you provide the Oxford RobotCar dataset you used in your paper? Thank you so much！