Yes, this is not the most recommendable way to do it. It is better to simply add each tensor to a list and concatenate them once at the end: ... <看更多>

tf.concat(concat_dim, values, name='concat') {#concat}. Concatenates tensors along one dimension. Concatenates the list of tensors values along dimension ... ... <看更多>

Just how to use tf.concat Function, that function concatenates tensor along one dimension you specified like this. tf.concat(list, dimension you ... ... <看更多>