-
Notifications
You must be signed in to change notification settings - Fork 114
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
Hyperparams for HRNet-48 #1
Comments
Hi I believe the model was trained with Adam (lr=1e-4, weight decay=1e-4). I trained for 100 epochs using batches of size 8. The augmentations differ a bit from the ones used in this repository. The random rescale was implemented as follows:
Note that in this piece of code the images used the PIL format instead of the open-cv format. Let me know if this is helfpul. |
Thank you for the response! I will try this. For this transform, have you used greyscale images, because it seems like img.size returns two outputs |
I did not include any color transformations like random grayscale or jitter. In this case, the |
Hello. Thanks very much for releasing the codes. Could you provide the config files for HRNet-48? I directly use the config file of HRNet-18 with just changing the backbone, but I cannot reproduce the ST and MT results like your paper. For ST task of segmentation, the mIoU is just 43%. For mutli-task training, I use batch size 4 due to memory limit, but multi-task learning performance on test set is -26.31 compared with ST. |
Hi. I used the same hyperparameters as for the HRNet-18 models. |
Thank you very much. Would you release your trained models for evaluation? |
I will probably do this as people are asking for it. But as I said, this will only be after the 16th of November. |
Hi, I'm currently trying to reproduce the best result of NYUD-v2. I have read this issue, and tried to set the same setting but I coudn't figure out that. You wrote you used the following augmentation, train_transforms = Compose([RandomHorizontallyFlip(), RandomRescale([1.0,1.2,1.5], (480,640))]) Could you make the setting a bit more clear? Your current code is set to use the following transforms: # Training transformations
# Horizontal flips with probability of 0.5
transforms_tr = [tr.RandomHorizontalFlip()] # <- Modify only here? Or, you used only the above transform?
# Rotations and scaling
transforms_tr.extend([tr.ScaleNRotate(rots=(-20, 20), scales=(.75, 1.25),
flagvals={x: p.ALL_TASKS.FLAGVALS[x] for x in p.ALL_TASKS.FLAGVALS})])
# Fixed Resize to input resolution
transforms_tr.extend([tr.FixedResize(resolutions={x: tuple(p.TRAIN.SCALE) for x in p.ALL_TASKS.FLAGVALS},
flagvals={x: p.ALL_TASKS.FLAGVALS[x] for x in p.ALL_TASKS.FLAGVALS})])
transforms_tr.extend([tr.AddIgnoreRegions(), tr.ToTensor(),
tr.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])
transforms_tr = transforms.Compose(transforms_tr) If you could tell me the right setting a bit more detailed, I would be really grateful. |
Hi. The augmentations used in this repo were implemented using the opencv (cv2) library. For the time being, I think you can use the train transforms I mentioned, and just add the ToTensor and Normalize operations. |
Hi, thank you for your reply. I know it needs some modifications, so I tried to implement the transforms using PIL. But the result was not the same as yours. I will test using the setting you replied again. Also, I'm looking forward to seeing your updates! |
I will rerun the code myself to make sure. But will probably be towards the end of the month. |
I am working to the fix the issue this week. |
I have made the code base consistent with the implementation used for the survey. The changes include the following:
At this point you should be able to get between 43.5 -- 44.0 MIoU using ResNet-50. |
Hi, Thanks again for your open-source code. I'm running your new code.And It seems your google drive can not be open .The data cannot be download. If you fix it, I would be really grateful. |
I see. I forgot to push the latest version of the nyud.py file. Should be fixed in the latest commit. |
Let me know if it works out now :) |
It works. Thanks! |
May I know which config file should we use to achieve this result with resnet-50? It looks like there is no Mti-net config on resnet-50? Thank you very much for your help. |
I did not include the code for MTI-Net using a ResNet-50 backbone. Currently it only supports an HRNet backbone for MTI-Net. |
@SimonVandenhende Thank you! |
Hi, I used batchsize=8 to train mti-net at 2 tasks(same hyperparameters as for the HRNet-18 models.). But I found the x_3_fpm['depth'].size() was [2, 384, 15, 20], In which the batchsize is equal to 2.not 8. Could you explain it ?Thanks a lot ! |
Hi. This could have to do with the specification of the number of backbone channels in |
Hi. I used HRNet-48 channels == [48,96,192,384 ] to train my network. But I also came cross that problem.I think I set right channels And the other problem is that: In your paper your performance is mIOU==49,rmse==0.529. Could you please tell me where is the problem in my training procedure. I have tried really hard to train it. Thank you so much! @SimonVandenhende |
I tried the experiment using HRNet-48. I got about 45.5 MIoU for the single-tasking model, while 47.0 MIoU for MTI-Net. The multi-task learning improvement was about 2.9 %. I think there are still some small differences with my old implementation used for the MTI-Net paper, which gave slightly better absolute numbers. Still, the conclusions from the paper are valid. Also, I advise to use the current implementation as it is inline with the one used for the survey paper. This should give you a fair comparison between architectures, as I spend quite some time finetuning the hyperparameters for every method, while also making sure that other implementation details like augmentations, etc. where the same among different methods. |
Hi, I noticed that in your latest HRnet-48 experiment, your MIoU is 47.0. Thanks! @SimonVandenhende |
Please could you let me know the hyperparams used to train the HRNet-48 model from your paper (both for the 45.7% mIoU and the ~49% mIoU scores)? I have tried really hard to train HRNet-48 on single task in my repository, but it doesn't go beyond 44.8% mIoU.
Thank you.
The text was updated successfully, but these errors were encountered: