wtyhub / lpn Goto Github PK

Hello,

Thank you for your great work.

I was trying to use the draw_cam.py script to extract heatmap from results, but there were some errors occured during the experiment, and I do not really understand the problem here:

Traceback (most recent call last):
File "draw_cam.py", line 115, in
draw_CAM(model, img_path, save_path, transform=data_transforms, visual_heatmap=False)
File "draw_cam.py", line 42, in draw_CAM
output.register_hook(extract)
File "/.pyenv/versions/anaconda3-2021.05/lib/python3.8/site-packages/torch/_tensor.py", line 289, in register_hook
raise RuntimeError("cannot register a hook on a tensor that "
RuntimeError: cannot register a hook on a tensor that doesn't require gradient

Could you check the script again and teach me how to solve this problem?
Thank you and best regards.

you said you reimplemented the SAFA with Pytorch in your paper, but I only found the reference of SAFA in your code like these.

Could you give me the definition code of SAFA?

hi，thank you for your great work.
the data link mentioned in the article : http://cs.uky.edu/~jacobs/datasets/cvusa/
is broken, can you provide a new dirve link of cvusa dataset.

Thank you and best regards.

Hello, I've been reading this code recently. I have a problem that I don't understand.

In the model.py file, the part_classifier function defined in the three_view_net function. During the training, the structure of the Classblock in this function is as follows:

During the test, the structure of classblock is as follows:

I want to ask, how is this achieved?

Hello, I downloaded the CVUSA dataset, but an error occurred when running prepare_ cvusa. py. There is no path in line 6 of the prepare_cvusa.py in my dataset. I want to know the directory structure of the CVUSA dataset to see if I downloaded the wrong dataset.

Hello, I had some problems while preparing for CVACT, as follows,
**dataset index: 218255 dataset unexist pair: ['G:/datasets/ANU_data_small/streetview/HkiKa_k0d5RXDxW14D_A1A_grdView.jpg', 'G:/datasets/ANU_data_small/satview_polish/HkiKa_k0d5RXDxW14D_A1A_satView_polish.jpg']**
This kind of prompt appeared many times. After processing, the 70G data finally generated only a 600M data. Can you tell me how to solve this problem?

Hello, when I run the prepare_cvact.py file, I am prompted that "No such file or directory:'./ACT_data.mat'. I want to ask if this file is in the CVACT dataset? The dataset I downloaded does not contain this file.

请问这个是否可以无视？

Hi, thanks for your code first. Can you offer the trained model on UNIVERSITY-1652?

Hi,

I directly trained the model to match images from two views (satellite -> drone) through the 'train.py', but the accuracy remained extremely low (from 0.0000 to 0.0060), and didn't grow with epoch increases.

I changed some of the parameters for training on my computer, the changes are as follow:
batchsize = 2
num_workers = 0
inputs2, labels2 are from the 'drone' directory
LPN = True

I wonder how I could achieve the accuracy. Are there any preparations upon the dataset needed before training? Thank you very much for your help!

Zhaoxiang

hi!
how get University-1652 dataset?

hi,Thanks for your work！
But when I was training CVUSA, the loss was always very large, and the accuracy rate was very low.
I have processed the dataset according to prepare_cvusa.py

-- Epoch 33/189

-- train Loss: 122.1055 Satellite_Acc: 0.0339 Street_Acc: 0.0411

-- Training complete in 450m 17s