hypercost

I only achieve Mean IoU: 0.7138 and Pixel-wise Accuracy: 93.72% with iteration 20000.

In your repo, the grad loss factor is set to 10. The reason is to make depth loss and grad loss in a same range? For example, 0.0x?

Which pretrained model did you use on the DND benchmark?

2

It is reported in your paper that > To this end, we evaluate on the recent Darmstadt Noise Dataset [34], consisting of 50 noisy images shot with four different cameras...

https://github.com/hszhao/PSPNet/blob/master/evaluation/prototxt/pspnet101_VOC2012_473.prototxt#L30

Compile error. Does it not support openv3 and above?

2

```bash CXX src/caffe/FRCNN/frcnn_proposal_target_layer.cpp In file included from ./include/caffe/FRCNN/util/frcnn_utils.hpp:25:0, from src/caffe/FRCNN/util/frcnn_bbox.cpp:1: /usr/include/opencv2/contrib/contrib.hpp:273:23: error: ‘vector’ does not name a type Octree( const vector& points, int maxLevels = 10, int minPoints = 20...

https://github.com/alterzero/DBPN-Pytorch/blob/master/main_gan.py#L123 Is this an error?

https://github.com/torchvideo/torchvideo/blob/master/src/torchvideo/internal/readers.py#L71 According to this https://stackoverflow.com/questions/2017843/fetch-frame-count-with-ffmpeg, Not all formats (such as Matroska) will report the number of frames resulting in the output of N/A. My video information: ``` ffprobe version 4.0...

https://github.com/Hangz-nju-cuhk/Vision-Infused-Audio-Inpainter-VIAI/blob/master/train_whole_sync.py#L10

Still have problems with preparing dataset?

1

I followed #4 to prepare Moving-mnist dataset. This is my code to generate .h5 file for training. ``` import numpy import h5py # Load data file = numpy.load( "moving-mnist-train.npz" )...