Skip to content

Instantly share code, notes, and snippets.

@ypwhs

ypwhs/random_seed_test.ipynb

Last active October 8, 2019 09:40
Show Gist options
  • Star 2 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save ypwhs/c54dc9031a408a31c71fa513c2da9945 to your computer and use it in GitHub Desktop.
Save ypwhs/c54dc9031a408a31c71fa513c2da9945 to your computer and use it in GitHub Desktop.
Download ZIP
Keras 固定随机数种子重现相同的训练结果
Display the source blob
Display the rendered blob
Raw
random_seed_test.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@yylonly
Copy link

yylonly commented May 15, 2018

我在google colab无法重现 你tf和keras版本是？

Train on 60000 samples, validate on 10000 samples
Epoch 1/2
60000/60000 [==============================] - 4s 61us/step - loss: 0.2117 - acc: 0.9365 - val_loss: 0.1123 - val_acc: 0.9645
Epoch 2/2
60000/60000 [==============================] - 3s 54us/step - loss: 0.0834 - acc: 0.9755 - val_loss: 0.0853 - val_acc: 0.9724
<keras.callbacks.History at 0x7f37e8751dd8>

Train on 60000 samples, validate on 10000 samples
Epoch 1/2
60000/60000 [==============================] - 4s 65us/step - loss: 0.2067 - acc: 0.9375 - val_loss: 0.1110 - val_acc: 0.9654
Epoch 2/2
60000/60000 [==============================] - 3s 53us/step - loss: 0.0805 - acc: 0.9759 - val_loss: 0.0831 - val_acc: 0.9735
<keras.callbacks.History at 0x7f37e87f2b38>

@ypwhs
Copy link
Author

ypwhs commented Apr 11, 2019

需要使用CPU运行。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment