0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 5 years have passed since last update.

MaskRCNNをtensorflow ver2で走らせるための実行環境及びエラー解決方法について

Last updated at Posted at 2020-05-09

備忘録として。

実行環境

GPU:RTX2080
tensoflow:2.0.0
CUDA:10.1
cuDNN:7.6.5.32

注意点として、下記の対応表だとtensoflowは2.1.0を使えとのことなんですが、model.pyを修正した上でdemoプログラムを走らせてみると「Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try to see if a warning log message was printed above.」とのエラーがでました。試しにtensoflowを2.0.0にしてみたら、エラーが出ずに実行できました。
https://www.tensorflow.org/install/source?hl=ja#gpu_support_2

model.pyの修正

エラー解決には下記を参考にしてmodel.pyを編集しました。
https://github.com/matterport/Mask_RCNN/issues/1797
https://github.com/matterport/Mask_RCNN/pull/1817/files

0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?