Open Hanawh opened 3 years ago
If I want to implement deeplabv2 in my own task,should the image preprocessing be same?like no padding,just resize
What are your image sizes in the train set and in the test set?
[640,480] resize and pad to [320,320]
If I want to implement deeplabv2 in my own task,should the image preprocessing be same?like no padding,just resize