sudo reboot

Looking forward to that too. ^_^

Setting 'theano.config.floatX = float32' might be useful

The images of training dataset have a shape of (127, 127, 3). So you need to resize your image to this shape so that the network can test the output...

不好意思回复晚了，单张的只需要修改这个for循环即可 https://github.com/heromanba/3D-R2N2-PyTorch/blob/18ceddbd5b1cf7d58cf56388f48337a1220b2a98/demo.py#L39

> > > 不好意思回复晚了，单张的只需要修改这个for循环即可 > > > https://github.com/heromanba/3D-R2N2-PyTorch/blob/18ceddbd5b1cf7d58cf56388f48337a1220b2a98/demo.py#L39 > > > > > > 您好，我已经改好了单张视图的测试代码，我将.obj文件使用meshlab打开，如何转换成背景无底色的单张视图呢？类似这种，谢谢您的回复 > >  > > 您好，我想问一下，3D-R2N2论文中给出的实验可视化结果，是怎么可视化出来的？ 我当时在mac上的xcode打开就是这样了，meshlab怎么导出不是很清楚哈

Hi, sorry to reply late. For configuration, you can refer to this file https://github.com/heromanba/3D-R2N2-PyTorch/blob/master/experiments/scripts/res_gru_net.sh For hardware, ``` +-----------------------------------------------------------------------------+ | NVIDIA-SMI 430.50 Driver Version: 430.50 CUDA Version: 10.1 | |-------------------------------+----------------------+----------------------+ |...