cuda deserialization issue

maudzung / Complex-YOLOv4-Pytorch

The PyTorch Implementation based on YOLOv4 of the paper: "Complex-YOLO: Real-time 3D Object Detection on Point Clouds"

https://arxiv.org/pdf/1803.06199.pdf

GNU General Public License v3.0

1.21k stars 260 forks source link

cuda deserialization issue #43

Open t-shubham opened 2 years ago

t-shubham commented 2 years ago

Attempting to deserialize object on CUDA device 2 but torch.cuda.device_count() is 1. Please use torch.load with map_location to map your storages to an existing device.

what to do?

i am running pretrained model

jacoblambert commented 2 years ago

change line 98 of test.py to

model.load_state_dict(torch.load(configs.pretrained_path, map_location=torch.device('cuda:0')))