search

agrimgupta92 / sgan

Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks", Gupta et al, CVPR 2018
MIT License
819 stars 260 forks source link

Question: Training error #14

Closed daehoumich closed 5 years ago

daehoumich commented 5 years ago

When I run the training commend: python scripts/train.py

I got an error message:

ValueError: could not convert string to float: '0.0\t1.0\t1.41\t-5.68' Any idea that can help me to fix it?

(When I run 'run_traj.sh', the training runs well).

Many thanks in advance.

agrimgupta92 commented 5 years ago

Refer delim option in https://github.com/agrimgupta92/sgan/blob/master/TRAINING.md#dataset-options. For you the delim should be '\t'.

daehoumich commented 5 years ago

It worked! Thank you so much.

Here is one more error: Traceback (most recent call last): File "scripts/train.py", line 580, in main(args) File "scripts/train.py", line 148, in main batch_norm=args.batch_norm) File "/home/daeho/sgan-master/sgan/models.py", line 425, in init if self.noise_dim[0] == 0:

Should I change noise_dim?

mingbocui commented 5 years ago

Hi,

I have the same problem with "ValueError: could not convert string to float: '0.0\t1.0\t1.41\t-5.68'". It is weird that this error still exists even if I have added " --delim '\t' "(also tried with --delim='\t'). Do you have any suggestions? Many thanks!

Warm regards

Fangyh09 commented 5 years ago

@mingbocui --delim "tab" works for me.