输入尺寸和输出尺寸的问题
Opened this issue · 3 comments
LanWong1 commented
我并没有看到在输入端把图像resize到1024512，仅仅是把短边等比例缩放到512，长边并没有固定到1024，为何输出的时候，就直接缩放到1024512呢？
class Decoder (nn.Module):
def init(self, num_classes):
super().init()
self.apn = APN_Module(in_ch=128,out_ch=20)
# self.upsample = Interpolate(size=(512, 1024), mode="bilinear")
# self.output_conv = nn.ConvTranspose2d(16, num_classes, kernel_size=4, stride=2, padding=1, output_padding=0, bias=True)
# self.output_conv = nn.ConvTranspose2d(16, num_classes, kernel_size=3, stride=2, padding=1, output_padding=1, bias=True)
# self.output_conv = nn.ConvTranspose2d(16, num_classes, kernel_size=2, stride=2, padding=0, output_padding=0, bias=True)
def forward(self, input):
output = self.apn(input)
out = interpolate(output, size=(512, 1024), mode="bilinear", align_corners=True)
# out = self.upsample(output)
# print(out.shape)
return out
Benjiaminh commented
我并没有看到在输入端把图像resize到1024_512，仅仅是把短边等比例缩放到512，长边并没有固定到1024，为何输出的时候，就直接缩放到1024_512呢？
class Decoder (nn.Module):
def init(self, num_classes):
super().init()self.apn = APN_Module(in_ch=128,out_ch=20) # self.upsample = Interpolate(size=(512, 1024), mode="bilinear") # self.output_conv = nn.ConvTranspose2d(16, num_classes, kernel_size=4, stride=2, padding=1, output_padding=0, bias=True) # self.output_conv = nn.ConvTranspose2d(16, num_classes, kernel_size=3, stride=2, padding=1, output_padding=1, bias=True) # self.output_conv = nn.ConvTranspose2d(16, num_classes, kernel_size=2, stride=2, padding=0, output_padding=0, bias=True) def forward(self, input): output = self.apn(input) out = interpolate(output, size=(512, 1024), mode="bilinear", align_corners=True) # out = self.upsample(output) # print(out.shape) return out
可以相互交流下不，我最近也在看这个，但是也有些问题，我的qq联系方式1602356172
Vieeo commented
LEDNet‘paras is 0.94M？Why I get 2.3M？About you？
HKQX commented
Resize函数会将另外一边按照原先图像比例乘以512 实际另外一边是2048%1024*512=1024，具体可以看函数说明