j96w/6-PACK

data_preprocess problem & training implementation problem

Opened this issue · 1 comments

xspkwy commented

  1. I followed the procedure of the datasets downloading and arrangement, but when I run data_preprocess.py, I got the problem:
    image
    So is it OK to ignore the missed files?

  2. I ignored the missed files, it seems some files are lost as below:

../My_NOCS/data/train/18690/0002_meta.txt
../My_NOCS/data/train/18690/0003_mask.png
../My_NOCS/data/train/18690/0009_mask.png
../My_NOCS/data/train/00469/0000_mask.png
../My_NOCS/data/train/00469/0001_mask.png
../My_NOCS/data/train/00469/0002_mask.png
../My_NOCS/data/train/00469/0004_mask.png
../My_NOCS/data/train/00469/0005_mask.png
../My_NOCS/data/train/00469/0007_depth.png
../My_NOCS/data/train/00469/0009_depth.png

  1. After ignoring the missed files and preprocessing them, I run train.py in the pytorch0.4.1 environment, but the training process stuck on the 1st epoch when train_count = 5000:
    image

So are there any suggestions? Thanks!

ymz1129 commented
  1. 我遵循了数据集下载和排列的过程，但是当我运行data_preprocess.py时，我遇到了问题：图像那么可以忽略丢失的文件吗？
  2. 我忽略了丢失的文件，似乎有些文件丢失了，如下所示：

../My_NOCS/data/train/18690/0002_meta.txt
../My_NOCS/data/train/18690/0003_mask.png
../My_NOCS/data/train/18690/0009_mask.png
../My_NOCS/data/train/00469/0000_mask.png
../My_NOCS/data/train/00469/0001_mask.png
../My_NOCS/data/train/00469/0002_mask.png
../My_NOCS/data/train/00469/0004_mask.png
../My_NOCS/data/train/00469/0005_mask.png
../My_NOCS/data/train/00469/0007_depth.png
../My_NOCS/data/train/00469/0009_depth.png

  1. 在忽略丢失的文件并对其进行预处理后，我在 pytorch0.4.1 环境中运行 train.py，但是当 train_count = 5000 时，训练过程卡在了第一个纪元：
    图像

那么有什么建议吗？谢谢！

Hi, I have the same file loss situation, but it seems like we are losing different data, we can check each other and exchange data to complete the training.
11b5245cf983a3487a263fc4dbbad65