qq184861643

Failed generate sample after tuning network architecture

2

I've changed your CausalConv1d as below: `class CausualConv1d(nn.Module): def __init__(self,in_channels,out_channels,kernel_size=2,stride=1,dilation=1,bias=True): super(CausalConv1d,self).__init__() self.pad = (kernel_size - 1) * dilation self.conv = nn.Conv1d(in_channels,out_channels,kernel_size,stride=stride,padding=self.pad,dilation=dilation,bias=bias) def forward(self,inputs): outputs = self.conv(inputs) return outputs[:,:,:-self.pad] ` And...

I meet "undefined reference"problem when cd build cmake .. make at around 84%. The problem has been solved. just add include_directories( "/home/finale/ORBSLAM2_with_pointcloud_map-master/g2o_with_orbslam2/" "/home/finale/ORBSLAM2_with_pointcloud_map-master/g2o_with_orbslam2/build" ) link_directories("/home/finale/ORBSLAM2_with_pointcloud_map-master/g2o_with_orbslam2/lib") in your CMakeList

code seems do not support resume training from a saved weight?

9

I was training a model using CASIA-Webface and it stopped in some where of total epochs accidentally. So I've add some lines in Learner.py and tried to resume training but...