Open seokyeongbaek opened 8 months ago
The qualitative results are generated with matplotlib. You can, for example, write the prediction results to a pickle file via test.py, and then plot the waypoints stored in the pickle file using matplotlib.
To obtain the metrics for shorter horizons, you can modify the input sent to the metric calculator. For example during updating min ADE, you can modify the code to be:
self.minADE.update(pred=traj_eval[:, :, :20, :self.output_dim], target=gt_eval[:, :20, :self.output_dim], prob=pi_eval, valid_mask=valid_mask_eval[:, :20])
to obtain minADE from 0 to 20.
Thank you for your response. I'll proceed as you suggested with the feedback!
Hi @seokyeongbaek Could you please share the code file if you have got the quantitative results(visualization).
hello.
I proceeded from QCNet train to validation for path prediction.
Could you please provide the ipynb file and code for visual testing such as Qualitative Results?
And, I am trying to validate a model already trained with num_future_steps =60, num_historical_steps=50. Can you please suggest the code to get minADE, minFDE for num_future_steps 0 to 10 or 0 to 20 in validation?