Question about preparing experiment when training

[lalaly0104]

Thank you for sharing！I followed the instructions and created the datasets.However，When I run ：python unsup_flow/cli.py --prod I got the following error：

Traceback (most recent call last): File "unsup_flow/cli.py", line 129, in <module> sys.exit(main_tf2()) # pragma: no cover File "unsup_flow/cli.py", line 56, in main_tf2 exp.prepare() File "./unsup_flow/experiment/experiment.py", line 189, in prepare self.cfg.data.name, File "./usfl_io/io_tools.py", line 1017, in get_unsupervised_flow_dataset check_dataset_interface(ds) File "./usfl_io/io_tools.py", line 959, in check_dataset_interface assert flat_out_shapes[k].as_list() == shape, (k, flat_out_shapes[k]) AssertionError: ('odom_t0_t1', TensorShape([None, 4]))

Can you tell me how to correct my mistake so that it can be trained properly?Thanks！