seann999
seann999
@clemense I am dealing with problem #1. How did you deal with it?
Got it; with some patience, I got around 5250 successfully simplified meshes (some seemed to take a really long time, which I killed and discarded)
Sorry, the program might require a newer version of TensorFlow. 2016/11/22 11:33 "liuhengli" [email protected]: > this function require pred_labels must have rank 2, but your program the > pred_labels shape...
I've added some instructions in the README.
Sorry about the late response. The cost is basically a negative log sum of rewarded glimpse locations and classic classification likelihoods. So the model not only learns to make better...
I was able to solve the above problem by going to the source and renaming 'blacklist' to 'denylist' Now I'm getting this: ``` --------------------------------------------------------------------------- TypeError Traceback (most recent call last)...
I was able to somewhat understand some of the data from reading the preprocessing scripts, but I do not understand how to obtain `sample_pts` in a real setting It seems...
Bump. I'm getting bad results with a real robot and I'm wondering if normalization has to do with it.
Bump again. I'm using ImageNet constants with mean [0.485, 0.456, 0.406] and std [0.229, 0.224, 0.225] but can't get decent results. It would be helpful if the example in the...
I think I simply did what I first guessed, x/128.0-1.0.