Open vieting opened 1 year ago
The failing tests are the ones from https://github.com/rwth-i6/pytorch-to-returnn/issues/125.
If we do this change, I have a follow up issue. The test cases work, but if I write the conversion result to a file via converter.get_returnn_config_serialized()
, the dim tags will show up at the beginning and are used in the network as well. Here is an example:
However, Linear_feature_dense_dim
in the example is not identical with the dim tag in the input. We would have to set the output dim tags also I guess, right? Are there already solutions for this in returnn_common or elsewhere?
You need to change all n_out
to out_dim
. This is for LinearLayer
but also other layers like ConvLayer
.
You also need to specify out_spatial_dims
for ConvLayer
.
I need to create them in create_returnn_layer_dict
and there is no way to infer them, right?
And the printed config will possibly have LOTS of dim tags at the beginning. I guess that's similar in returnn common, right?
As discussed in #134, it is currently not possible to do a convolution over the axis which RETURNN considers the feature dim and it would be helpful to set
in_dim
. However, then the basic_get_output_shape_from_returnn
fails because there, the new feature dim is mapped to the old feature dim and as a result, the remaining dims are also mapped incorrectly. I add a suggestion in this PR.