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).
Thank you for your coding. I want to use my own images to train the model. So when I label my images, I just need to label them like "xxxxgtFine_labelIds.png " .Other file such as ".json" and other ".png" file is not needed, right?
Thank you for your coding. I want to use my own images to train the model. So when I label my images, I just need to label them like "xxxxgtFine_labelIds.png " .Other file such as ".json" and other ".png" file is not needed, right?