somebodyus

Why the `SegNet_ConvLSTM` and `SegNet` output `F.log_softmax(up1, dim=1)`? The Cross Entropy loss function has already the softmax operation.

What is the difference between train_index and train_index_new?

1

I have downloaded your dataset from google drive. What is the difference between `train_index.txt` and `train_index_new.txt`, `val_index.txt` and `val_index_new.txt`? Which one did you use in your paper? I also find...

Could you upload the complete text index?

benchmark results are not accordance with the results presented in the dvo_slam paper

4

Dear author, I successfully compile the dvo_slam package in ROS fuerte on Ubuntu 12.04.5. I use the default ROS openni calibration parameters. I benchmark the dataset "rgbd_dataset_freiburg1_xyz" using the following...

Could you update the code with the latest g2o version?

not work with conv3d

How to augment an image with channel number larger than 3?

8

How to augment an image with channel number larger than 3? Specifically, I have an RGB-D image. The channel number is 4.