search

yurimjeon1892 / EFGH

EFGHNet: A Versatile Image-to-Point Cloud Registration Network for Extreme Outdoor Environment
18 stars 3 forks source link

Running error #9

Open LoveMYChen opened 1 month ago

LoveMYChen commented 1 month ago

=> using 'cuda' for computation. => checking ckpt dir... => creating model and optimizer... Traceback (most recent call last): File "main.py", line 238, in main() File "main.py", line 126, in main model = nets.dictargs['arch'] + 'Backbone'.to(device) File "/home/hdp/EFGH/nets/efghbackbone.py", line 16, in init self.E = Enet(args)
File "/home/hdp/EFGH/nets/enet.py", line 22, in init self.generate_data = GenerateData(dim, scales_filter_map, self.device)
File "/home/hdp/EFGH/nets/generate_data.py", line 51, in init traversal.go(center, hash_table) File "/home/hdp/EFGH/nets/transforms.py", line 111, in go self.walk_cuboid(start_key, 0, False, walking_keys, hash_table_list) File "/home/hdp/EFGH/nets/transforms.py", line 119, in walk_cuboid self.walk_cuboid(walking_keys[d], d + 1, has_zero or (i == 0), walking_keys, hash_table_list) File "/home/hdp/EFGH/nets/transforms.py", line 119, in walk_cuboid self.walk_cuboid(walking_keys[d], d + 1, has_zero or (i == 0), walking_keys, hash_table_list) File "/home/hdp/EFGH/nets/transforms.py", line 119, in walk_cuboid self.walk_cuboid(walking_keys[d], d + 1, has_zero or (i == 0), walking_keys, hash_table_list) File "/home/hdp/EFGH/nets/transforms.py", line 120, in walk_cuboid walking_keys[d] = advance_in_dimension(self.d + 1, 1, d, walking_keys[d]) TypeError: expected dtype object, got 'numpy.dtype[int64]'

LoveMYChen commented 1 month ago

I installed numba and encountered the following error ImportError: cannot import name 'cffi_support' from 'numba' (/home/hdp/anaconda3/envs/efgh/lib/python3.8/site-packages/numba/init.py) May I ask which version is correct？

LoveMYChen commented 1 month ago

Have solved. Thanks!