DOLG issues

crop for DELG?

Hi, thanks for sharing your re-implementation of DELG in pytorch, that helps me a lot! By the way, is the performance of DELG-R101(GLDv2-clean) in Table 1 of your paper obtained...

Maryeon

错误堆栈为： Traceback (most recent call last): File "evaler/infer.py", line 119, in main_multicard data = extract(im, model) File "evaler/infer.py", line 62, in extract global_feature = model(input_data) File "/home/tiger/workspace/anaconda/envs/DOLG/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in...

sandy-ssdut

desc_top1_err and desc_top5_err are always 100 during training

4

@feymanpriv Thanks for your great work! When I fine-tune the DOLG model on my customized dataset using your model weight, the desc_top1_err and desc_top5_err are always 100. I am not...

JiahaoXia

Weights for pre-trained models

3

Hi, I like your work and I am interested in testing the pre-trained models, but I seem not able to download them from Baidu via the provided links. Is it...

jenicek

关于revisitop 数据集feature的pkl文件

您好，很感谢您提供了这么棒的工作。我最近在尝试复现您的工作，但是我遇到了一些问题，希望能得到您的回复。关于您仓库中提供的 Roxford 和 Rpairs 数据集的 pickle 文件，我尝试使用 Roxford 和 Rpairs 数据集的图像和您提供的模型权重进行复现，并测试结果。这是我用您的模型文件和您提供的roxford_R101_512_crop_test5.pickle文件在 Roxford 上的测试结果。这是我用您的模型文件[R-101-DOLG](https://pan.baidu.com/s/1_osEyC53txA-_1cbadBzLQ) 在Roxford数据集上用您的evaler/infer.py提取的特征roxford_R101_512_crop_test5_reproduce.pickle，使用您提供的模型权重在 Roxford 上的测试结果。二者在 E M H 上mAP 都有不小的 drop。所以想问下您，您提供的pkl文件是用您放出的模型权重 [[R-50-DOLG] 或者 [R-101-DOLG]生成的吗？...

sd0809

How to download the Roxford5k and rparis6k dataset

1

Hello, I want to know how to download the oxford5k and the rparis6k dataset, which contain the images and labels.

Cindy-zhangtong

配置文件中的BASE_LR和论文里的initial learning rate是什么关系

12

按照代码里的配置完成了训练，发现过程中学习率最高只有BASE_LR参数设定的0.01，对比论文4.1节中提及的initial learning rate为0.05，请问是否应将BASE_LR修改为0.05？论文所说的initial learning rate是指warm up前第一个epoch的学习率，还是warm up后第6个epoch的最大学习率？

SheldonHS