Comments (4)
Below is a detailed error report.
Traceback (most recent call last):
File "train.py", line 39, in
main()
File "train.py", line 33, in main
train_dataloader=train_loader)
File "core/train/trainers/monohuman/trainer.py", line 177, in train
net_output = self.network(**data)
File "/home/yejr/miniconda3/envs/Monohuman/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "core/nets/monohuman/network.py", line 609, in forward
all_ret = self._batchify_rays(packed_ray_infos, **kwargs)
File "core/nets/monohuman/network.py", line 273, in _batchify_rays
ret = self._render_rays(rays_flat[i:i+cfg.chunk], **kwargs)
File "core/nets/monohuman/network.py", line 502, in _render_rays
T_joints=canonical_joints)
File "core/nets/monohuman/network.py", line 201, in _query_mlp
rgb_feat=rgb_feat)
File "core/nets/monohuman/network.py", line 236, in _apply_mlp_kernals
dis, _ = closest_distance_to_points(T_joints, SMPL_PARENT, xyz)
File "core/nets/monohuman/network.py", line 81, in closest_distance_to_points
p_index = parent[min_index]
RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)
from monohuman.
Below is a detailed error report.
Traceback (most recent call last): File "train.py", line 39, in main() File "train.py", line 33, in main train_dataloader=train_loader) File "core/train/trainers/monohuman/trainer.py", line 177, in train net_output = self.network(**data) File "/home/yejr/miniconda3/envs/Monohuman/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl return forward_call(*input, **kwargs) File "core/nets/monohuman/network.py", line 609, in forward all_ret = self._batchify_rays(packed_ray_infos, **kwargs) File "core/nets/monohuman/network.py", line 273, in _batchify_rays ret = self._render_rays(rays_flat[i:i+cfg.chunk], **kwargs) File "core/nets/monohuman/network.py", line 502, in _render_rays T_joints=canonical_joints) File "core/nets/monohuman/network.py", line 201, in _query_mlp rgb_feat=rgb_feat) File "core/nets/monohuman/network.py", line 236, in _apply_mlp_kernals dis, _ = closest_distance_to_points(T_joints, SMPL_PARENT, xyz) File "core/nets/monohuman/network.py", line 81, in closest_distance_to_points p_index = parent[min_index] RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)
Hi, I didn't encounter this error. Please check if you have modified any code. And It seems that the 'min_index' in GPU course the error. Just put 'min_index' to CPU will fix it.
from monohuman.
The problem has been solved, thank you
May I also ask if Monohuman can train together with multiple GPUs?
from monohuman.
The problem has been solved, thank you May I also ask if Monohuman can train together with multiple GPUs?
It did not support DDP training yet. I will update it later. Thanks.
from monohuman.
Related Issues (20)
- 关于MonoHuman训练的一些问题 HOT 3
- 关于cuda和pytorch版本问题 HOT 2
- cannot import name 'PRIO_PGRP' from 'os' HOT 1
- Help Regarding Skeleton Plotting on Image with transformation HOT 1
- How to get the index_a and index_b in config file? HOT 2
- Question about observation bank HOT 1
- Question about evaluation HOT 1
- Train from the lastest checkpoint HOT 2
- about joints -= pelvis_point[None, ] HOT 1
- Can reconstruct 3d model? 能重建和导出三维模型吗? HOT 1
- Data preprocessing problem HOT 1
- 请教关于人体运动差异 HOT 1
- How to train on multiple Gpus HOT 2
- 关于Forward Correspondence Search Module的理解 HOT 1
- About videos in the wild HOT 3
- Error in the Evaluation Code HOT 2
- error in training HOT 2
- How much memory of GPU is needed for training? HOT 2
- Annotation files for Human3.6m dataset HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from monohuman.