-
Hi, I have an issue evaluating the descriptors using --descr-dir argument.
I've downloaded the sift descriptors and saved in **_root/data/descriptors/sift/_**. And when I'm in the folder of _**pyth…
-
Hi Wei,
thanks for sharing the code.
Would it be possible to provide the ETH3D evaluation code?
I was wondering how the data flow of the model's forward propagation.
Look forward to your reply…
-
Hi folks,
I downloaded HPatches package, as well as sift and orb descriptors (e.g. `sh download.sh descr sift`). It turned out that for each patch per sequence(image), there exists one and only on…
-
May I ask what is your final indicator, and how much is the difference from the paper? Like coco recall?
-
I use your r2d2_WASF_N16.pt to evaluate on HPatches , I get the MMA@3 = 0.721 , the same as your data, but I get the m-score only 0.292, Can you tell me some details about your m-score evaluation code…
-
After generate.py is used, will the size of the image produced be different from the original image, which will have an impact on the evaluation? It's different with HPatches. Thank you!
-
I want to ask if my trianing steps are right? Could you tell me? step1 -> step2 -> step3 ->step2 ->step3(maybe repeat 2->3 some times) ->step6 -> step7 I don't want to evaluating the repeatability …
-
Sorry, but I got a problem when running the code in the docker,
No file is found under the directory "/home"
Looking forward to your reply, Thanks.
Uooga updated
4 years ago
-
Would you consider to release the training code for the deep learning descriptors?
-
seem like that the pretrained model privided is not rubust agsinst Rotation,Right？