New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Comparing with ExtremeNet and CornerNet #269
Comments
One more query: Were the pretrained ExtremeNet weights (which you used to initialize Hourglass for COCO) trained originally with channels in RGB order (like other pytorch pretrained models) or BGR? Thanks. |
@bsvineethiitg did you check also this L1loss CenterNet/src/lib/models/losses.py Line 184 in a5a0483
Here they average on the all pixels (128^2) but in the paper, they average on the non-zeros pixels (which is the true raisoning)! |
Thanks for the question. This turns out to be the major reason for this work being rejected. CenterNet training from scratch (100epochs) gives |
By "scratch" you mean ImageNet or MPII weights for Hourglass, right? |
Centernet is my favourite detector. It's ridiculous to reject it for this reason. |
Thanks @chenyuntc ! This means a lot to us. |
@bsvineethiitg "scratch" means using random initialization. |
Hi @xingyizhou . Quick clarification please. So, the model for COCO-HG you reported on the paper (40.3 / 42.2 / 45.1), you said that was finetuned from ExtremeNet (50epochs) + CornerNet (~200epochs). I want to reproduce that. Which pretrained model should I use for this? Is it "ExtremeNet_500000.pth"? I'm confused because you referred to that as the 100 epoch ExtremeNet model in your above comment. Is ExtremeNet_500000.pth in your Drive link the 100 epoch ExtremeNet model or (50 epoch ExtremeNet starting from CornerNet 200 epoch) model? |
You are correct. |
If you have trained your model on the 100 epoch ExtremeNet using the following command (with the same LR and #gpus and batch sizes): python main.py ctdet --exp_id coco_hg --arch hourglass --batch_size 24 --master_batch 4 --lr 2.5e-4 --load_model ../models/ExtremeNet_500000.pth --gpus 0,1,2,3,4 --num_epochs 50 --lr_step 40 could you please share it in the google drive please? Also, I'd be glad if you can confirm if you trained that exactly with above command. |
Hello bsvineethiitg, have you tried this command? And can you reproduce the result? |
Since COCO hourglass starts with pretrained ExtremeNet weights which was in turn pretrained on CornerNet weights, is it fair to compare CenterNet to those models? Because effectively, CenterNet is trained for a lot more epochs when you include the epochs that went into the pretraining.
Also, can you point me to the pretrained weights that you used for training the hourglass model on COCO? Thanks.
The text was updated successfully, but these errors were encountered: