Seq2Seq(Attention)Input Shape Question

Seq2Seq(Attention)\Seq2Seq(Attention)-Tensor.py

The shape of the input should be [max_time, batch_size,...]. The input = tf. transpose (dec_inputs, [1, 0, 2]) has already been transformed. In tf. expand_dims (inputs [i], 1), the expansion is indeed one dimension. It seems that there should be zero dimension expansion here. Although the final shape is correct, whether it is intentional or not is here. What about a little trick?

Read Seq2Seq(Attention)\Seq2Seq(Attention)-Tensor.py and trace the shapes through the transpose and tf.expand_dims(inputs[i], 1) expressions. Run the example and compare each intermediate shape with the stated [max_time, batch_size, ...] expectation. Done means deciding whether the expansion is intentional and documenting or correcting the behavior.

Rédigé par le modèle d'indexation à partir du texte de l'issue.