gidobot / silhonet Goto Github PK

I would like to detect the best Grasp point in YCB_Video datasets, but I don't know how to create the Grasp point detection datasets. I find you have made the precomputed Grasp Points datasets. Could you tell me how to create the precomputed points? If possible, Could you provide the datasets for me? Thanks for your assistance.

When I run "matlab -nodesktop -nosplash -r gen_full_silhouettes " , I get an error.
This function 'load_obj_file' is undefined in

"gen_full_silhouettes (line 47)
obj = load_obj_file(file_obj);"

Thanks for your code~
I find some error in ycb.py:
def get_model(self, im_index, cls_idx): ims = [] f_list = glob.glob(osp.join(self._model_path, self._classes[cls_idx], '*_albedo.png')) for f in f_list: ims.append(read_im(f)) return np.stack(ims, axis=0)
ERROR:
File "/media/wislab/Data/LDY/SilhoNet/ycb.py", line 750, in fetch_data data_list = self.load_ycb(self._image_index[idx]) File "/media/wislab/Data/LDY/SilhoNet/ycb.py", line 709, in load_ycb 'im_mdl': self.get_model(im_index, cls_idx), File "/media/wislab/Data/LDY/SilhoNet/ycb.py", line 542, in get_model return np.stack(ims, axis=0) File "/home/wislab/anaconda2/envs/py3/lib/python3.6/site-packages/numpy/core/shape_base.py", line 350, in stack raise ValueError('need at least one array to stack') ValueError: need at least one array to stack
And there's not any picture with "_albedo.png" in "data/models/[class]/", what's problem with this?