Closed Jaeyoung-Lim closed 2 years ago
Problem Description When manually selecting data using the data selection tool, the pipeline fails with the following error
------------------------------------------------------------------------------- Optimization Metrics ------------------------------------------------------------------------------- R2: 0.9998888927269959 RMSE: 0.058325590518898365 ------------------------------------------------------------------------------- Complete results saved to: model_results/multirotor_model_2022-02-16-13-46-30.yaml ------------------------------------------------------------------------------- Traceback (most recent call last): File "Tools/parametric_model/generate_parametric_model.py", line 117, in <module> start_model_estimation(**vars(arg_list)) File "Tools/parametric_model/generate_parametric_model.py", line 99, in start_model_estimation model.compute_residuals() File "/home/jaeyoung/dev/data-driven-dynamics/Tools/parametric_model/src/models/dynamics_model.py", line 486, in compute_residuals y_forces_pred[2::3] = y_pred[int(2*self.y_forces.shape[0]/3):self.y_forces.shape[0]] ValueError: could not broadcast input array from shape (5414) into shape (14075) Makefile:34: recipe for target 'estimate-model' failed make: *** [estimate-model] Error 1
It appears that the residual calculation is done on the full log, while the predictions are done on the selected data, which was added in https://github.com/ethz-asl/data-driven-dynamics/pull/182
Fixed in https://github.com/ethz-asl/data-driven-dynamics/pull/191
Jaeyoung-Lim
commented
2 years ago Jaeyoung-Lim
commented
2 years ago
Problem Description When manually selecting data using the data selection tool, the pipeline fails with the following error
It appears that the residual calculation is done on the full log, while the predictions are done on the selected data, which was added in https://github.com/ethz-asl/data-driven-dynamics/pull/182