Objection detect code

[C-C-Y]

Hello, may I ask when the code for object detection will be released? I look forward to your response. Thank you.

[rayleizhu]

The MM project series share the same backbone usage. Hence it is not difficult to transfer the segmentation code to detection.

As you asked, I will arrange the release in two weeks.

[C-C-Y]

The MM project series share the same backbone usage. Hence it is not difficult to transfer the segmentation code to detection.

As you asked, I will arrange the release in two weeks.

Thank you very much.

[LMMMEng]

Thank you for your wonderful work! Could you please release the config file for the detection first?

[rayleizhu]

Thank you for your wonderful work! Could you please release the config file for the detection first?

Maybe by next Friday. I cannot guarantee as there are many other things on my hand. But I'm sure the full detection code can be released in two weeks.

[Hiyao-yy]

Thanks for sharing, looking forward to the full detection code！

[rayleizhu]

The object detection code has been released.

Note that you need to update the environment if you have done setup previously.

[LMMMEng]

Thanks for your effort, I wonder if norm eval can improve performance

BiFormer/object_detection/models_mm/biformer_mm.py

Line 30 in 8c6f0f7

self.norm_eval = norm_eval

Moreover, could you let me know what the bugs are on the normalization layer?

[rayleizhu]

Thanks for your effort, I wonder if norm eval can improve performance

I did not remember how much it helps. You may have a try. If you have a conclusion, please tell me here. By the way, norm_eval=True is the default choice of mmdetetction:

BiFormer/object_detection/configs/_base_/models/mask_rcnn_r50_fpn.py

Line 12 in 8c6f0f7

norm_eval=True,

Moreover, could you let me know what the bugs are on the normalization layer?

See my comments here:

BiFormer/object_detection/models_mm/biformer_mm.py

Line 50 in 8c6f0f7

# NOTE: in the version before submission:

Actually, I do not know if it is this modification that works. There are some other differences (not in my model but functions or environment provided by third parties), as I mentioned in the README.

[LMMMEng]

Thanks for your effort, I wonder if norm eval can improve performance

I did not remember how much it helps. You may have a try. If you have a conclusion, please tell me here. By the way, norm_eval=True is the default choice of mmdetetction:

BiFormer/object_detection/configs/_base_/models/mask_rcnn_r50_fpn.py

Line 12 in 8c6f0f7

norm_eval=True,

Moreover, could you let me know what the bugs are on the normalization layer?

See my comments here:

BiFormer/object_detection/models_mm/biformer_mm.py

Line 50 in 8c6f0f7

# NOTE: in the version before submission:

Actually, I do not know if it is this modification that works. There are some other differences (not in my model but functions or environment provided by third parties), as I mentioned in the README.

Many thanks!