Results 11 issues of Weijian Xu

Thank you for the repo! I can reproduce the SAN-10 pairwise / patchwise results. However, for the CNN baselines mentioned in this paper (i.e. ResNet-26, ResNet-38, ResNet-50), I wonder how...

When I tried to extract the pairs from the training set (use annotations of non-zero style and create pairs using same pair_id & style but different source), it will have...

Hi! I have some questions about the design of Match R-CNN: 1) What are the coefficient lambda_1 ~ lambda_5 in the loss function L? 2) I would like to know...

1. According to the paper, the feature extractor of match-net has 4-conv layers, one pooling layer and one fc layer. Are these layers: -- Conv1: 3x3 conv - 256 channels...

1. In the retrieval task, the paper mentions that 12 epochs are used for training. I wonder what is the definition of 1 epoch. Does it mean all image pairs?...

The projection function `proj()` in [droid_slam/geom/projective_ops.py (L44)](https://github.com/princeton-vl/DROID-SLAM/blob/main/droid_slam/geom/projective_ops.py#L44) has a threshold for Z. Similar thresholding for Z is also applied in [projective_transform()](https://github.com/princeton-vl/DROID-SLAM/blob/main/droid_slam/geom/projective_ops.py#L112) to generate a valid map. I am confused about...

I used the command below to perform the experiment (environment: Python 3.6 / TensorFlow 1.10): ``` # 1-shot 5-way Mini-ImageNet. python -u run_miniimagenet.py --shots 1 --inner-batch 10 --inner-iters 8 --meta-step...

Update: NVM. Already preprocessed the ImageNet dataset.

Hi all. Recently I wrote a PyTorch version of HED and got ODS=0.787 OIS=0.807 which is similar to the Caffe version (ODS=0.788 OIS=0.806 on my machine). https://github.com/xwjabc/hed Hope it can...

Hi, I would like to know if the versions of libraries in the `requirements.txt` can be provided. Currently I am using the latest TF (2.11) that seems to have breaking...