'Non-existent config key: MODEL.MASKIOU_ON' while running demo.py about centermask2 HOT 10 CLOSED

@Auth0rM0rgan

As I said, you should fine the best MAX_SIZE_TEST suitable for your task (e.g., speed, resolution, etc).

I think MAX_SIZE_TEST of 128 is too small to detect.

How about 512?

from centermask2.

Having same problem here.

from centermask2.

@youngwanLEE, I think your demo.py is broken. Having the same problem here.

from centermask2.

@Auth0rM0rgan @denverdash @Rm1n90
I fixed demo.py.
Would you like to try again?

from centermask2.

Hey @youngwanLEE, Still demo.py not working

my command line:

python demo.py --config-file ../configs/centermask/centermask_V_39_eSE_FPN_ms_3x.yaml --video-input /home/xx/Downloads/avg.mp4

The error I'm getting is:

File "demo.py", line 14, in <module> from centermask.config import get_cfg ModuleNotFoundError: No module named 'centermask'
Thanks!

from centermask2.

@youngwanLEE having same error as @Auth0rM0rgan!

from centermask2.

@Rm1n90 @Auth0rM0rgan

Would you like to try again?

from centermask2.

@youngwanLEE,
Thanks, demo.py is working now.
Also, I have a question regard to Fps on 1080p video. Which one of your lite pretrained model is suitable to reach 30fps for instance segmentation on 1080P video?
I have tried all the lite pretrained models on my 1080p video but none of them could reach to 30fps. I have also tried the YOLACT 550 with ResNet50 and I was able to achieve almost ~25fps on 1080p video. according to your paper, CenterMask is faster than YOLACT but in my test yolact do the instance segmentation faster. any tips?

Thanks!

from centermask2.

@Auth0rM0rgan

While Our demo program originates from detectron2, YOLACT visualization tools are optimized well for better speed.

Inference time in many papers is usually measured using the only model forward time not including visualization step.

We also follow detectron2 rule.

I recommend you use lite models such as V-19-slim or V-19-slim-dw.

And,

if you lower the 'MAX_SIZE_TEST', you can get faster speed.

python demo/demo.py ... --opts INPUT.MAX_SIZE_TEST 512

In conclusion,

1. Select well-balanced (speed and accuracy) models
2. Lower MAX_SIZE_TEST
3. Search the best combination between the model and MAX_SIZE_TEST to the extent you accept.

from centermask2.

Hey @youngwanLEE, Thanks for the tips but when I set the INPUT.MAX_SIZE_TEST i'm not getting any output (I mean code is working but masks are not overlay on the objects)

python demo.py --video-input /home/Downloads/tennis_720.mp4 --config-file ../configs/centermask/centermask_V_39_eSE_FPN_ms_3x.yaml --opts MODEL.WEIGHTS ../centermask2-V-39-eSE-FPN-ms-3x.pth INPUT.MAX_SIZE_TEST 128

When my command line is without INPUT.MAX_SIZE_TEST everything works fine and masks are overlaying on top of objects. Thanks!

from centermask2.