-
hi, i want to inference with ur trained superpoint parameters
here is my use of your cli_tool,
`#!/bin/bash
set -e
# folders param
TAG=testResult_coco_1_sppoint4 #example
IMAGES=/data/SiLK/da…
-
Hi, thanks for the great work. From reading your FAQ:
> `Checkpoint`. We provide two checkpoints for our VGG-4 backbone : pvgg-4.ckpt and coco-rgb-aug.ckpt (trained with different photometric augme…
-
I'm having a bit of trouble understanding the architecture for this project.
1. Input an image of some size `HxW` is provided at the start of the network. In the [Demo](https://github.com/MagicLea…
-
Thank you for your awesome works.
I noticed you provided an example of exporting the dense silk model as torch script. However, when I changed the setup to use sparse feature points and sparse des…
-
Dear author, thanks for your great work! Recently i'm trying to reproduce your results, and i have some problem about it.
For training, I use your default setting(only change bs=8) to train TopicF…
-
Hello，rpautrat, sorry to disturb you. The following error confuse me when i ran the first step, so could you give me some suggestion?
2021-05-23 12:22:40.944712: I tensorflow/core/common_runtime/gp…
-
Thank you for sharing this wonderful work!
I am testing your results on HPatches, however I am not sure which keypoint scale (sampling window) you utilized when testing BEBLID descriptor. I noticed t…
-
A lot of the performance heavy parts of Pawnmorpher like MutationTracker.CompTick() run every second, which can cause some slowdowns for games, as pawnmorpher will easy use up 1ms average with all its…
-
Hello, when I evaluated the HPatches dataset, I found that eval_hpatches_generate_plot.ipynb calls the files in the path datasets\hpatches\cache-top\. I want to know how these files are generated in t…
-
你好，感谢代码的开源，有两个问题请教一下。
1.cross norm中的track_running_stats是设置为False吗？
2.cross norm的输出是否还需要加L2 norm，因为用到了余弦距离。