-
Notifications
You must be signed in to change notification settings - Fork 74k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
in nmt_with_attention, the gru in decoder is not connected, last step state is not passed to this step #38248
Comments
Hello, I'd like to work on this issue. Can you plz give me some pointers on where I should start? |
I think you're right. @ManishAradwad if you want to take a shot at a fix, I think all it needs is a |
Be careful with that. The last time I did that, the attention plots didn't come out right. So please test and see if the attention plots remain similar to what they are now. The |
@MarkDaoust |
Thanks for taking a look @hihell
Can you be more specific? I'll dive in and try to figure out what's wrong. |
I tried re-running the notebook with |
@MarkDaoust |
@MarkDaoust |
I'm working on this now. |
- Use the TextVectorization layer. - Use the AdditiveAttention layer. - tf.function the translate loop for text->text export. - Add more inline explanations, and sanity checks. - Add shape assertions throughout the code to make it easier to follow. Fixes tensorflow/tensorflow#38248 PiperOrigin-RevId: 370168273
Fixed in 9e18593 |
For TF2.5 - Use the TextVectorization layer. - Use the AdditiveAttention layer. - tf.function the translate loop for text->text export. - Add more inline explanations, and sanity checks. - Add shape assertions throughout the code to make it easier to follow. Fixes: tensorflow/tensorflow#38248 Fixes: tensorflow/tensorflow#39654 See also: tensorflow/tensorflow#49237 PiperOrigin-RevId: 370250185
For TF2.5 - Use the TextVectorization layer. - Use the AdditiveAttention layer. - tf.function the translate loop for text->text export. - Add more inline explanations, and sanity checks. - Add shape assertions throughout the code to make it easier to follow. Fixes: tensorflow/tensorflow#38248 Fixes: tensorflow/tensorflow#39654 See also: tensorflow/tensorflow#49237 PiperOrigin-RevId: 370250185
For TF2.5 - Use the TextVectorization layer. - Use the AdditiveAttention layer. - tf.function the translate loop for text->text export. - Add more inline explanations, and sanity checks. - Add shape assertions throughout the code to make it easier to follow. Fixes: tensorflow/tensorflow#38248 Fixes: tensorflow/tensorflow#39654 See also: tensorflow/tensorflow#49237 PiperOrigin-RevId: 370250185
For TF2.5 - Use the TextVectorization layer. - Use the AdditiveAttention layer. - tf.function the translate loop for text->text export. - Add more inline explanations, and sanity checks. - Add shape assertions throughout the code to make it easier to follow. Fixes: tensorflow/tensorflow#38248 Fixes: tensorflow/tensorflow#39654 See also: tensorflow/tensorflow#49237 PiperOrigin-RevId: 375597559
https://www.tensorflow.org/tutorials/text/nmt_with_attention
the decoder is trained step by step, and it's not passing last step state to this step
is this a feature or a bug? I checked a lot of NMT with attention paper, unlike the document those decoder are connected.
thanks in advance!
The text was updated successfully, but these errors were encountered: