search

JaveyWang / Pyramid-Attention-Networks-pytorch

Implementation of Pyramid Attention Networks for Semantic Segmentation.
GNU General Public License v3.0
235 stars 55 forks source link

上采样这儿是不是核大小应该为3？ #12

Open ReckonerInheritor opened 4 years ago

ReckonerInheritor commented 4 years ago

self.conv_upsample_2 = nn.ConvTranspose2d(channels_mid, channels_mid, kernel_size=4, stride=2, padding=1, bias=False) 改为： self.conv_upsample_2 = nn.ConvTranspose2d(channels_mid, channels_mid, kernel_size=3, stride=2, padding=1, bias=False) 这样修改正确吗？