-
Notifications
You must be signed in to change notification settings - Fork 255
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
使用额外bvh文件进行retargeting #213
Comments
您好,根据你的描述我猜测这里的问题有可能是你所使用的数据集在“正面”上的定义和Mixamo不太一样导致的。也许可以尝试一下对这个问题进行修正过后(即将正常动作的正面也换到T-pose的正面)再进行retargeting。 |
感谢回复~ 我把数据集修正了一下重新训练模型产出的结果确实正常了很多 |
您好,这个章节介绍了生成蒙皮的脚本 |
目前没有mean和var是用不了预训练模型的 |
李老师:
您好,感谢你们在重定向方面开源了这么棒的工作,受益匪浅。我在你们的数据集上实验均没有问题,但是使用自己的数据集bvh进行训练时发现效果不佳,我用的数据集是Trinity Speech-Gesture dataset,在blender中打开具有这样的特点:正常动作面朝的方向与Tpose相反,如下图
针对该数据集新定义了简化后的骨骼
corps_name_trinity = ['Hips', "LeftUpLeg", "LeftLeg", "LeftFoot", "LeftForeFoot", "LeftToeBase", "RightUpLeg", "RightLeg", "RightFoot", "RightForeFoot", "RightToeBase", 'Spine', 'Spine1', 'Spine2', "Spine3", 'Neck', 'Neck1', 'Head', 'LeftShoulder', 'LeftArm', 'LeftForeArm', 'LeftHand', 'RightShoulder', 'RightArm', 'RightForeArm', 'RightHand'] 共26个
并以此进行preprocess,构建完数据集后将其作为groupA,原数据集中xxx-m依然作为groupB,训练了1w多epoch,测试后发现骨骼的朝向好像有问题,导致整个骨骼很扭曲,但是大致动作能看出与输入动作的一致性
希望李老师能给个大概思路,可能是哪里存在问题,谢谢~期待您的回复
The text was updated successfully, but these errors were encountered: