search

uber-research / UPSNet

UPSNet: A Unified Panoptic Segmentation Network
Other
648 stars 120 forks source link

What is the acronym "ch" stand for? #87

Closed liushuchun closed 5 years ago

liushuchun commented 5 years ago

Hi, thanks for your great work. I have try to learn your code, but feel confused about the post processing part, 

        def get_pred(pan_2ch_all, color_gererator, cpu_num=None):
            if cpu_num is None:
                cpu_num = multiprocessing.cpu_count()
            pan_2ch_split = np.array_split(pan_2ch_all, cpu_num)
            workers = multiprocessing.Pool(processes=cpu_num)
            processes = []
            for proc_id, pan_2ch_set in enumerate(pan_2ch_split):
                p = workers.apply_async(BaseDataset._converter_2ch_single_core, (proc_id, pan_2ch_set, color_gererator))
                processes.append(p)
            workers.close()
            workers.join()
            annotations, pan_all = [], []
            for p in processes:
                p = p.get()
                annotations.extend(p[0])
                pan_all.extend(p[1])
            pan_json = {'annotations': annotations}
            return pan_all, pan_json

what is the "ch" in "pan_2ch_all" represents for?