clelouch

Thanks for your repo. Have you considered supporting 3D convolution?

in models.py line 184 ` :param cmap_lengths: character sequence lengths, a tensor of dimensions (batch_size, word_pad_len)` the shape of cmap_lengths should be (batch_size)?

Hi, thanks for your code! After reading the code and your paper, I have some questions. 1. You wrote in your paper that you do not enforce the ratio test...

#9 When i use matlab script to evaluate descriptors like hardnet and geodesc, I modify the matlab/data/best_normalizations.csv.  After that, I run the run_article.m and res_article.m in sequence. However, I...

How to get the Fig.1 in paper?

2

 Thanks for your code and paper. I'm curious about the visualization of low-level and high-level features. Could your please tell me how to generate such a figure?

how to define the "converge" of the training loss

5

Thanks for your code and paper. I notice that there is no validation set in the training stage. and the training process is stopeed when the loss converges. I am...

seems to a bug?

3

 it seems that the mask_scores = 0.3 * mask_iou + bbox_score

Thanks for your great work. In your code, mask_on== false indicates instance segmentation task while mask_on ==True indicates object detection. In D2Det.py  In D2Det_head.py  But when mask_on==false, the...

The convolutional layers in localization network

4

Hi, thanks for your code. I want to plug the STN into a CNN, and after comparing your code with the code in[ pytorch tutorial](https://pytorch.org/tutorials/intermediate/spatial_transformer_tutorial.html), I find some differences. ...

A question about DWG

1

Thanks for your code and paper. In your implementation, the DWG is proposed to evaluate the reliability of spatial and temporal features and it assigns different weights to features at...