search

huanghoujing / beyond-part-models

PCB of paper: Beyond Part Models: Person Retrieval with Refined Part Pooling, using Pytorch
331 stars 81 forks source link

Average pooling #15

Closed a462428 closed 6 years ago

a462428 commented 6 years ago

Hi,

in paper, there is an average pooling before 1x1Conv

however, I don't know where is it in your model?

self.base = resnet50( pretrained=True, last_conv_stride=last_conv_stride, last_conv_dilation=last_conv_dilation) self.num_stripes = num_stripes

self.local_convlist = nn.ModuleList() for in range(num_stripes): self.local_conv_list.append(nn.Sequential( nn.Conv2d(2048, local_conv_out_channels, 1), nn.BatchNorm2d(local_conv_out_channels), nn.ReLU(inplace=True) ))

huanghoujing commented 6 years ago

Thanks for your attention! The average pooling is here.