sum_nap

` strategy.run_backtest() File "/opt/conda/lib/python3.8/site-packages/QAStrategy/qactabase.py", line 192, in run_backtest risk = QA_Risk(self.acc) File "/opt/conda/lib/python3.8/site-packages/QUANTAXIS/QAARP/QARisk.py", line 184, in __init__ self._assets = self.account.daily_cash.set_index( File "/opt/conda/lib/python3.8/site-packages/QUANTAXIS/QAARP/QAAccountPro.py", line 636, in daily_cash index=pd.to_datetime(self.trade_range_max).set_names('date'), File "/opt/conda/lib/python3.8/site-packages/QUANTAXIS/QAARP/QAAccountPro.py", line...

how to achieve the performance in .img/learning_curve.jpg?

1

I wonder to know if the performances in ./img/learning_curve.jpg is the final result by fine-tone with the pre-trained model. I've done a lot of work to achieve the same result（such...

How to generate the json file?

1

Thanks for your work! I wonder to know how to generate the json label file? I notice that the marks parameters in json label files are added 2 value relative...

overlap threshold {0.5, 0.25, 0.25} need to be changed as official {0.7, 0.5, 0.5}

3

There is a problem in eval code(evaluate_object_3d_offline.cpp), the overlap threshold should be changed as official {0.7, 0.5, 0.5}. Now it's {0.5, 0.25, 0.25}(for 3d and image/ground plane).