search

autonomousvision / occupancy_networks

This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"
https://avg.is.tuebingen.mpg.de/publications/occupancy-networks
MIT License
1.48k stars 291 forks source link

demo on the CPU #91

Open riccardosemprevivo opened 3 years ago

riccardosemprevivo commented 3 years ago

I get this error when i try to run the demo on the cpu:

python generate.py configs/demo.yaml https://s3.eu-central-1.amazonaws.com/avg-projects/occupancy_networks/models/onet_img2mesh_3-f786b04a.pt => Loading checkpoint from url... Traceback (most recent call last): File "generate.py", line 46, in checkpoint_io.load(cfg['test']['model_file']) File "/home/ubuntu/Documents/occupancy_networks-master/im2mesh/checkpoints.py", line 47, in load return self.load_url(filename) File "/home/ubuntu/Documents/occupancy_networks-master/im2mesh/checkpoints.py", line 78, in load_url state_dict = model_zoo.load_url(url, progress=True) File "/home/ubuntu/anaconda3/envs/mesh_funcspace/lib/python3.6/site-packages/torch/utils/model_zoo.py", line 67, in load_url return torch.load(cached_file, map_location=map_location) File "/home/ubuntu/anaconda3/envs/mesh_funcspace/lib/python3.6/site-packages/torch/serialization.py", line 367, in load return _load(f, map_location, pickle_module) File "/home/ubuntu/anaconda3/envs/mesh_funcspace/lib/python3.6/site-packages/torch/serialization.py", line 538, in _load result = unpickler.load() File "/home/ubuntu/anaconda3/envs/mesh_funcspace/lib/python3.6/site-packages/torch/serialization.py", line 504, in persistent_load data_type(size), location) File "/home/ubuntu/anaconda3/envs/mesh_funcspace/lib/python3.6/site-packages/torch/serialization.py", line 113, in default_restore_location result = fn(storage, location) File "/home/ubuntu/anaconda3/envs/mesh_funcspace/lib/python3.6/site-packages/torch/serialization.py", line 94, in _cuda_deserialize device = validate_cuda_device(location) File "/home/ubuntu/anaconda3/envs/mesh_funcspace/lib/python3.6/site-packages/torch/serialization.py", line 78, in validate_cuda_device raise RuntimeError('Attempting to deserialize object on a CUDA ' RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location='cpu' to map your storages to the CPU.

mitesuti commented 1 year ago

Hello.

I, too, would like to run this program on my CPU. However, I am getting many errors at compile time. (like m.lib not found...) Were you able to finally run it on cpu? Also, I would like to know if there are any changes or innovations you made at that time.

Best regards