How to inference?

[guofeng1996]

My inference command is :python demo/image_demo.py 2.jpg configs/sspnet/faster_rcnn_r50_sspnet_1x_coco_new.py checkpoints/epoch_10.pth --device cuda:3

Traceback (most recent call last):
File "demo/image_demo.py", line 50, in
main(args)
File "demo/image_demo.py", line 30, in main
result = inference_detector(model, args.img)
File "/home/SSPNet-master/mmdet/apis/inference.py", line 129, in inference_detector
data = test_pipeline(data)
File "/home/SSPNet-master/mmdet/datasets/pipelines/compose.py", line 41, in call
data = t(data)
File "/home/SSPNet-master/mmdet/datasets/pipelines/loading.py", line 61, in call
corner = results['img_info']['corner']
KeyError: 'corner

How can I fix it? or How to inference a image?

[MingboHong]

You need to modify the “test_pipeline” in “coco_detection.py”

test_pipeline = [
dict(type='LoadSubImageFromFile') ===> dict(type='LoadImageFromFile')
xxxxx
xxxxx
xx
]

where "dict(type='LoadImageFromFile')" avoids the use of patch images for inference.

[guofeng1996]

Thank you very much. I did it!

[guyuehuqaq]

You need to modify the “test_pipeline” in “coco_detection.py”

test_pipeline = [ dict(type='LoadSubImageFromFile') ===> dict(type='LoadImageFromFile') xxxxx xxxxx xx ]

where "dict(type='LoadImageFromFile')" avoids the use of patch images for inference.

Is your reasoning page like this? I use your open source code, the accuracy is always a few points lower, can you tell me what's going on?please