Tomandjob
Tomandjob
> in main.py > please note: > > with open(os.path.join(FLAGS.out_dir, 'FLAGS.json'), 'w') as f: > flags_dict = {k:flags.FLAGS.__flags[k] for k in flags.FLAGS.__flags} > json.dump(flags_dict, f, indent=4, sort_keys=True, ensure_ascii=False) > >...
> Hi, I've provided the related codes, you can execute `python datasets/UCAS_AOD/ucas_aod2gt.py` to convert to dst format. Hi, the annotation format of my dataset is xml. How do I use...
> Thanks for your reply. This content seems to be correct. I changed some parameters and it worked fine.
> See FAQ "Q: I failed to train the network or get the right solution, e.g., large training loss, unbalanced losses." and "Q: Implement new losses or constraints." I reviewed...
@praksharma Thank you for your reply. The right codes should be `A=x*y` and `0.5*dy_xx + dA_x`. The predicted solution of the neural network is very small and fluctuates around 0....
@praksharma Yes, this is an approximate method. I don't know how to define this condition precisely yet.
I had that problem too.