Deephome opened a new issue #13572: How to use ndarray.contrib.DeformableConvolution ? URL: https://github.com/apache/incubator-mxnet/issues/13572 I define a module performing deformable convolution as follows, but I do not know how to save the parameters (self.weight, self.bias) of this module using "net.save_parameters()" ... class DeformConv2D(nn.Block): def __init__(self,in_channel,num_filter,kernel=(5,5),pad=(2,2),stride=(1,1)): super(DeformConv2D, self).__init__() self.in_channel = in_channel self.num_filter = num_filter self.kernel = kernel self.pad = pad self.stride = stride self.weight = nd.normal(loc=0.,scale=1.,shape=(num_filter,in_channel,kernel[0],kernel[1]),ctx=gpu()) self.bias = nd.zeros((num_filter,),ctx=gpu()) self.weight.attach_grad() self.bias.attach_grad() def forward(self, inputs, offset): if self.weight.context != inputs.context: self.weight = self.weight.copyto(inputs.context) self.bias = self.bias.copyto(inputs.context) outputs = ndarray.contrib.DeformableConvolution(data=inputs, offset=offset,weight=self.weight,bias=self.bias, kernel=self.kernel, num_filter=self.num_filter,pad=self.pad,no_bias=self.no_bias) return outputs
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
