I've upgrade my tensorflow and keras with this code:
!pip install tf-nightly-gpu-2.0-preview
Now every epoch of model learning cost 22 min which was 17 sec before this upgrade!!! I did downgrade tensorflo and keras but it did not help!
You can reset your backend using the Runtime -> Reset all runtimes... menu item. (This is much faster than kill -9 -1
, which will take some time to reconnect.)
Ok. It's solved. just restore everything in colab by this code:
kill -9 -1
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.