Felipe Codevilla
Felipe Codevilla
Here it goes: using IMGAUG st = lambda aug: iaa.Sometimes(0.4, aug) oc = lambda aug: iaa.Sometimes(0.3, aug) rl = lambda aug: iaa.Sometimes(0.09, aug) self.augment = iaa.Sequential([ rl(iaa.GaussianBlur((0, 1.5))), # blur...
Hey @pri2si17-1997 It means the frequency the augmentation is applyed. St means for 40% of the images ( sometimes) Oc is for 30% of the images ( ocasionally) Rl is...
Hey @histfuture I was not able to reproduce this error. Could you provide some more information ? Did you set the town correctly ? Remember, this reinforcement learning code is...
Throttle 0.5 is like a minimum to beat the inertia in carla physics.
Thanks for the question BTW. @paulaurel Yeah, but it goes very very slow right ? On 0.5 it like already input some constant speed. Inertia was not the right term....
Hello @Florence-C For the CARLA paper, the loss function was 0.45 for steer, 0.05 for brake and 0.45 for gas. This is for each command branch. Then there is the...
Hey lvlvlvlvlv, Yes the steering is mostly small. I think for your case, the trick is to balance the data. Make sure that every minibatch covers a good range of...
Hey @jackspp The dataset I provided is about 12 hours and it was used on the CARLA paper. The noise flag was not used in the end but the noise...
There is one in tensorflow. by merantix https://github.com/merantix/imitation-learning I have one in pytorch that am trying hard to release it soon. I am just waiting because I need to finish...
Mine is here. https://github.com/felipecode/coiltraine/