The problem of image shape

[xiewende]

when use "python3 train.py --config configs/voc_cac_deeplabv3+_resnet50_1over8_datalist0.json" with two GPUS to run , i find that one GPUS imput image size is (1,3,335,500) while another is (1,3,366,500) . in this case ,i can run to end.
but ,when i run with only one GPU,the problem of diffrent size is occr.
how is go ???

[X-Lai]

Thanks for your interest in our work. I don't really understand your problem. Can you clarify your question more clearly?

[xiewende]

run with only one Gpu , a problem of diffrent input image size
run with two Gpus , one GPUS input image size = (1,3,335,500) while another GPUS input image size = (1,3,366,500)，but in this case，i can run
what happen? why the input image size is different

[X-Lai]

Do you meet the problem only in validation? If yes, I recommend you to adjust the batch_size in val_loader to be the same as n_gpu. Since during validation, the size of images are different.

[xiewende]

ok！thank to your answer！however，how i train with my own datasets，and what mean under dataloaders TXT file ，is there any py_file to generate these txt_file?