Youngwan Lee

sh make.sh errors under pytorch version '1.0'.

7

### System information * Operating system: Ubuntu 18.04 * CUDA version: CUDA v10 * cuDNN version: cuDNN v7.3 * GPU models (for all devices if they are not all the...

Hi, Is there the program or function that computes computational complexity(FLOPs) of this Dectectron model?

How to make VOC07+12 TFRecords

6

Hi, First of all, Thanks for your excellent implementation ! I already made VOC2007 TFRecord files. Then, I have a question how to make VOC 07+12 TFRecord that is union...

Hi, I'm very impressed by your work. I wonder whether you have a plan to do experiments that transfer your pre-trained model to downstream tasks such as object detection as...

reproduced result is low on ResNet backbone

22

I tried to reproduce the result(78.43%) of ResNet backbone in README.MD just by using [this command](https://github.com/jfzhang95/pytorch-deeplab-xception/blob/master/train_voc.sh). Of course, I prepared for SBD dataset and train the model on VOC2012 +...

benchmark result on val

2

Hi, Could you let me know how to evaluate and benchmark on Cityscapes testset? I can't figure out how to save the segmentation result by submission format. Thanks in advance.

Hi, I'm very impressed by your work. I have a question. Could you provide us with the computational cost (FLOPs) of TPN? I3D + TPN or TSM + TPN models....

about visualization code for Figure.5

1

Hi, I'm very impressed by your work. Could you share the code for visualization as in Figure.5 ??

Hi, I want to train my [WR-Inception Networks](https://arxiv.org/abs/1702.01243) from scratch by using Keras. Could you give me some advices ? Thanks in advance.

Hi, I want to know accuracy of your implementation.