deeplabv3
deeplabv3 copied to clipboard
Loss of information: upscaling after downscaling in get_item
https://github.com/fregu856/deeplabv3/blob/415d983ec8a3e4ab6977b316d8f553371a415739/datasets.py#L74
In get_item, you resize image to 50% of original dimensions. Then, you randomly scale downscaled image to 70-200%. In the case of upsamplig to 200%, information about original image has been lost. Wouldn't it be best to work with original image if upscaling by factor of <100% ?