image size doesn't match model

fudan-zvg / SETR

[CVPR 2021] Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

MIT License

1.05k stars 149 forks source link

image size doesn't match model #39

Closed mxmdpc closed 2 years ago

mxmdpc commented 3 years ago

Hello: when test pascal_context dataset, output: AssertionError: Input image size (389480) doesn't match model (480480).

sixiaozheng commented 2 years ago

Yes, the input of pascal VOC dataset must be 480x480, please check again if the environment is installed correctly. Please refer to the A from-scratch setup script in the README.md to reinstall the environment. And run the command ./tools/dist_train.sh ${CONFIG_FILE} ${GPU_NUM}.