MagNet

MagNet copied to clipboard

On the Cityscapes dataset experiment, the input size of the backbone network is set to 256×128, and the original image size is 2048×1024, and the input samples are obtained by...

DwRolin

Hi, First of all, thank you for your excellent work. However, I have a small question about Deepglobe dataset. 1. As far as I know, the original validation and test...

Jack-bo1220

# of required GPUs to reproduce Best outputs

10

Hello ! Thanks for your great contribution in this field. I'm setting up to follow your work (MagNet) and wonder how many GPUs are required to implement your codes? In...

yswang1717

input to the model

1

Does your model have to require a picture with a size of 1024*2048?

hmQ1998

RuntimeError: shape '[1, 1, -1, 508, 508]' is invalid for input of size 16451136

2

zcq-debug

RuntimeError: shape '[1, 1, -1, 508, 508]' is invalid for input of size 16451136

1

RuntimeError: shape '[1, 1, -1, 508, 508]' is invalid for input of size 16451136

xuyichengyy

About the result of deepglobe dataset

5

hi！ For the deepglobe dataset, I have some questions about the results of the replication. This is the result of my own training backbone network and refined modules：  I...

hly1999

RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

1

i run the scripts offered in the part "To test with a Deepglobe image", using the python demo.py ......, then i got the followling error: "RuntimeError: indices should be either...

littlezbq

My problem is same as the link: #https://github.com/VinAIResearch/MagNet/issues/11 Could you provide the filenames of train and test, and share me the label you used? Thank you so much!

BubbleSai

demo.py: error: --sub_batch_size

2

usage: demo.py [-h] --dataset DATASET [--root ROOT] [--datalist DATALIST] --scales SCALES --crop_size N [N ...] --input_size N [N ...] [--num_workers NUM_WORKERS] --model MODEL --num_classes NUM_CLASSES --pretrained PRETRAINED [--pretrained_refinement PRETRAINED_REFINEMENT [PRETRAINED_REFINEMENT...

yongjilee