search

prismformore / Multi-Task-Transformer

Code of ICLR2023 paper "TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding" and ECCV2022 paper "Inverted Pyramid Multi-task Transformer for Dense Scene Understanding"
MIT License
297 stars 23 forks source link

We assume all the images have the same size!!! #19

Closed khawar-islam closed 1 year ago

khawar-islam commented 1 year ago

Dear @prismformore

I am running inference file based on single image downloaded from the internet. Also, I successfully installed all libraries without downloading Cityscapes dataset because I do not want to train a model.

CUDA_VISIBLE_DEVICES=0 python3 inference.py --config_path=configs/pascal/pascal_vitLp16_taskprompter.yml --image_path=fff.jpeg --ckp_path=TaskPrompter_pascal_vitLp16.pth.tar --save_dir=output

Input fff

Traceback

/home/cvpr/anaconda3/envs/ICCV2023/lib/python3.7/site-packages/torch/nn/functional.py:3635: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
  "See the documentation of nn.Upsample for details.".format(mode)
/media/cvpr/CM_24/Multi-Task-Transformer/TaskPrompter/utils/visualization_utils.py:122: UserWarning: Warning: We assume all the images have the same size!!!
  warnings.warn('Warning: We assume all the images have the same size!!!')
prismformore commented 1 year ago

@khawar-islam Hi, this is just a warning. Did you get any error?

Please also check the discussion here for visualization of 3D detection results on Internet images. Normally the model only works with those using camera parameters of Cityscapes stuttgart split here.