LEDNet

LEDNet copied to clipboard

the pretrained model on cityscapes

8

could you send the pretrained model of cityscapes to me? my email address is [email protected] thank you!

xuxiuzhi2627

can not download the trainmodel

13

where is the train model ? could you share the trained model?

10183308

Hi everyone, has someone pretrained the encoder with the imagenet dataset and can send me the model? Thank you!

christinaionescu

输入尺寸和输出尺寸的问题

3

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 =...

LanWong1

could you send the pretrained model on cityscapes dataset to me?Thank you

xuxiuzhi2627

预训练模型 链接失效

1

作者你好，感谢你的贡献以及公开代码！但你给的预训练模型链接失效了。 能重新分享一下吗。非常感谢

noobliang

_This is something that I encountered when I was executing the code on another dataset. So I modified the code in a way that it can support other datasets as...

pranav-gupta-7

Link to model is broken

1

I tried to download the trained weights but the link to models is broken.

shafu0x

@xiaoyufenfei hi when i try to visual cityscapes annotation on the data by extraction of semattic maps from png i get the following results is there any best way to...

abhigoku10

Hi, how is the loss weights (0 ~19) calculated? Based on the number of images? or the number of pixels?

BorisChen1998