Comments (1)
感谢分享您的工作! 在使用重定向的工程中,我使用了lafan1的骨架作为输入,但当运行demo.py后,出现如下模型加载的问题,请问这种情况我是需要使用该骨架重新训练吗?
Traceback (most recent call last): File "eval_single_pair.py", line 97, in main() File "eval_single_pair.py", line 76, in main model.load(epoch=20000) File "E:\python\motion_editing\retargeting\models\architecture.py", line 274, in load model.load(os.path.join(self.model_save_dir, 'topology{}'.format(i)), epoch) File "E:\python\motion_editing\retargeting\models\integrated.py", line 82, in load self.auto_encoder.load_state_dict(torch.load(os.path.join(path, 'auto_encoder.pt'), map_location=self.args.cuda_device), False) File "E:\anaconda\lib\site-packages\torch\nn\modules\module.py", line 1483, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for AE: size mismatch for enc.layers.0.0.mask: copying a param with shape torch.Size([184, 92, 15]) from checkpoint, the shape in current model is torch.Size([176, 88, 15]). size mismatch for enc.layers.0.0.weight: copying a param with shape torch.Size([184, 92, 15]) from checkpoint, the shape in current model is torch.Size([176, 88, 15]). size mismatch for enc.layers.0.0.bias: copying a param with shape torch.Size([184]) from checkpoint, the shape in current model is torch.Size([176]). size mismatch for enc.layers.0.0.offset_enc.bias: copying a param with shape torch.Size([184]) from checkpoint, the shape in current model is torch.Size([176]). size mismatch for enc.layers.0.0.offset_enc.weight: copying a param with shape torch.Size([184, 69]) from checkpoint, the shape in current model is torch.Size([176, 66]). size mismatch for enc.layers.0.0.offset_enc.mask: copying a param with shape torch.Size([184, 69]) from checkpoint, the shape in current model is torch.Size([176, 66]). size mismatch for enc.layers.0.1.weight: copying a param with shape torch.Size([96, 184]) from checkpoint, the shape in current model is torch.Size([96, 176]). size mismatch for dec.layers.1.1.weight: copying a param with shape torch.Size([184, 96]) from checkpoint, the shape in current model is torch.Size([176, 96]). size mismatch for dec.layers.1.2.mask: copying a param with shape torch.Size([92, 184, 15]) from checkpoint, the shape in current model is torch.Size([88, 176, 15]). size mismatch for dec.layers.1.2.weight: copying a param with shape torch.Size([92, 184, 15]) from checkpoint, the shape in current model is torch.Size([88, 176, 15]). size mismatch for dec.layers.1.2.bias: copying a param with shape torch.Size([92]) from checkpoint, the shape in current model is torch.Size([88]). size mismatch for dec.layers.1.2.offset_enc.bias: copying a param with shape torch.Size([92]) from checkpoint, the shape in current model is torch.Size([88]). size mismatch for dec.layers.1.2.offset_enc.weight: copying a param with shape torch.Size([92, 69]) from checkpoint, the shape in current model is torch.Size([88, 66]). size mismatch for dec.layers.1.2.offset_enc.mask: copying a param with shape torch.Size([92, 69]) from checkpoint, the shape in current model is torch.Size([88, 66]). size mismatch for dec.unpools.1.weight: copying a param with shape torch.Size([184, 96]) from checkpoint, the shape in current model is torch.Size([176, 96]). size mismatch for dec.enc.layers.0.0.mask: copying a param with shape torch.Size([184, 92, 15]) from checkpoint, the shape in current model is torch.Size([176, 88, 15]). size mismatch for dec.enc.layers.0.0.weight: copying a param with shape torch.Size([184, 92, 15]) from checkpoint, the shape in current model is torch.Size([176, 88, 15]). size mismatch for dec.enc.layers.0.0.bias: copying a param with shape torch.Size([184]) from checkpoint, the shape in current model is torch.Size([176]). size mismatch for dec.enc.layers.0.0.offset_enc.bias: copying a param with shape torch.Size([184]) from checkpoint, the shape in current model is torch.Size([176]). size mismatch for dec.enc.layers.0.0.offset_enc.weight: copying a param with shape torch.Size([184, 69]) from checkpoint, the shape in current model is torch.Size([176, 66]). size mismatch for dec.enc.layers.0.0.offset_enc.mask: copying a param with shape torch.Size([184, 69]) from checkpoint, the shape in current model is torch.Size([176, 66]). size mismatch for dec.enc.layers.0.1.weight: copying a param with shape torch.Size([96, 184]) from checkpoint, the shape in current model is torch.Size([96, 176]).
我也遇到相同的问题,请问你解决了吗
from deep-motion-editing.
Related Issues (20)
- How the the skining work? HOT 1
- 处理过手指的重定向吗? HOT 3
- Retargeting retraining on customized dataset HOT 3
- 非标准躯干数据集的可能性 HOT 8
- Use a new dataset in style transfer HOT 1
- 使用额外bvh文件进行retargeting HOT 6
- style transfer任务的pretrained模型和提供config不符
- BVH_mod HOT 1
- Error in forward kinematics HOT 2
- 请问作者有没有尝试过面向3d坐标的异构重定向?
- Error: No module named 'option_parser'
- Error: No module named 'datasets'
- Error: No such file or directory: './datasets/Mixamo/Malcolm_m.npy'
- 您好,我现在面临在经过Preprocessing处理之后,在训练的时候数据打开verbose选项,看到数据都是Nan,请问这可能是什么原因造成的呢 HOT 1
- the src.bvh and dst.bvh must be the same Skeletal hierarchy ?
- retarget a bvh file to use it in style transfer HOT 1
- What is the equivalent for batch overfitting for such a training scheme?
- 关于其它bvh文件retargeting的几个问题?
- full body BVH with fingers
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 deep-motion-editing.