Fariz Rahman
Fariz Rahman
@raubitsj This is a superset of that PR (it wasnt tagged so I had no idea it existed). I have updated the description for this PR.
Hi, the problem is with the embeddings.. I am working on an example chatbot for seq2seq, will take some time.
Shape of your model is not compatible with your training data.
@nicolas-ivanov Did you try the other models? Seq2seq, Seq2seq with peek, Attention Seq2seq etc?
I recently tested attention seq2seq on the babi dataset and it worked (100% val acc).
The standard babi dataset from facebook (used by keras in examples). I did it using a slightly different layer but the idea is almost as same as attention seq2seq. I...
Please post your code.
@daniel-falk This is because normal dataset iteration does not download or decompress the samples, but tensorflow iteration does. To get a fair comparison, try doing `sample['image'].numpy()` in the ds iteration.
@daniel-falk You can get faster iteration by passing `fetch_chunks=True` to your `.numpy()` call. We are looking into how we can enable this by default for iteration. ```python import tqdm import...
Closing as fixed by #1887