Andy
Andy
ok, thanks your answer, What I mean is how to run a single server with multi-card training, not distributed training
okay, thanks for your answer, I will try it
thank your advice, i have tried multiple gpu by with tf.device('/gpu:i'%i), but it always hits 已杀死, i have debugged many times, but it not solved! followings are some my run...
same the problem i meet, i have no idea, have you solved this bug? thanks @rajatsharma369007
> 非常高兴收到你的及时回复 # @PeizhuoLi 👍 还有一些问题想请教一下: 1)使用默认的数据集训练非常缓慢,在Linux服务器(8卡,Tesla P100,8 * 16GB)上大约48个小时跑了约2000个epoch,是不是哪里设置有问题? 2)我想用预训练模型测试第三方bvh模型的重定向效果,由于我测试的bvh拓扑结构和已训练的模型都不同,我尝试把我的bvh拓扑结构手动修改为BigVegas(Skeleton type = 10)拓扑结构,在Mixamo文件夹下新建test文件夹,把修改后的bvh文件(无运动信息)命名为Dancing Running Man.bvh,同时拷贝该文件到std_bvhs文件夹下,运行 example('Aj', 'test', 'Dancing Running Man.bvh', 'intra', './examples/intra_structure') 运行过程无异常,result.bvh并不是期望的结果  左边是Aj,中间是BigVegas,右边是我们按照BigBegas修改的bvh模型 这可能是什么原因引起的?我理解如果是相同的拓扑结构是不需要重新训练的对吧? > > 谢谢!...
> https://github.com/facebookresearch/supervision-by-registration > > > 训练模型后使用python调用摄像头进行跟踪,发现关键点抖动很明显,有什么方法可以解决? > > > > > > You can refer to this simple implement , https://github.com/610265158/Peppa_Pig_Face_Engine, > > checking the demo to see if it...
> 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,...
> 如果只有一个静态的bvh文件,骨骼是T-pose姿态 怎么得到正确的mean 和 var 尼 ,我用preprocess.py跑出来的数据,去跑预训练模型,得到的结果 是错误的  你好,很认真看了你的问题,我也有同样的疑问, 1、如果只是一个静态的bvh文件,跑preprocess.py会直接报错,你也有这样的问题吗 2、静态的bvh文件,你跑通了demo.py 中的retargting过程吗 期待你的回复
> Hi @SteveJunGao Can you please release the pre-trained model for building images as mentioned in the paper? +1 can you release the pre-trained model for building images ? @SteveJunGao
> Hi, I have question here. > The "test" mode are fine ,the results are nice, but the "refer test" mode results are very blurry.I saved the cycle image(used for...