DeepLab-v3-plus-cityscapes
DeepLab-v3-plus-cityscapes copied to clipboard
mIOU=80.02 on cityscapes. My implementation of deeplabv3+ (also know as 'Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation' based on the dataset of cityscapes).
How can i change the batch-size?
作者你好!非常感谢你的代码,我看到您的val是自己写的代码,请问如何使用cityscape的官方测试脚本来测试您的模型?非常感谢您的工作,期待您的回复!
The site for download of pretrained model don't accept italian number, can you put in another platform like Google drive please? I need this for my degree thesis
Is it possible to visualize the output of the evaluation in form of images?
hi, Why does the interface get stuck when I run the code? Thanks