graykode / graykode/nlp-tutorial
seq2seq(attention) have wrong comment
Open
- Dominant language
- Jupyter Notebook
- Stars
- 14.9k
- Forks
- 3.9k
- PR merge metrics
- No merged PRs in 30d
Description
```
context = tf.matmul(attn_weights, enc_outputs)
dec_output = tf.squeeze(dec_output, 0) # [1, n_step]
context = tf.squeeze(context, 1) # [1, n_hidden]
```
I think dec_output shape is [1,n_hidden]
Contributor guide
Assessment
This issue has not been assessed yet.