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
Unstable training #1
Comments
Hello, @alwynmathew! |
I used exact same data and hyperparameters you have used in the demo notebook. |
Ok, I'll examine it. There were some issues with the parameters. Meanwhile you can play with our pretrained model - it was trained for 75 epochs with lr=1e-2; batch=20 (You may try to learn with the parameters). Or a better one - it was trained for extra 35 epochs with lr=1e-4 (with the first model as pretrain). |
I have also ported original monodepth to pytorch here. I faced the exact same issue that the disparities get degraded after few epochs. What are the hyperparameters you used to get better results? |
lr=1e-2; batch=20 is good enough (see above) for our implementation |
@NikolasEnt |
Hello, @alwynmathew! Once again. Are you sure you downloaded correct dataset as described here? |
Hi @Sparkling-Brick, according to the notebook provided in the repo, the data loader is just loading from one of the kitti dataset subfolder |
Yes. Thanks for noting it, the path was changed to check whether notebook working or not before publishing. However if you noticed that path in the notebook is just for one subfolder you should be able to change it to load the whole dataset. |
But @Sparkling-Brick do you think just added more data will solve the problem? The original implementation used batch size as small as 8, why do you recommend higher batch size? |
Hi, @alwynmathew, we retrain our model from scratch with the following parameters: 'model':'resnet18_md',
'learning_rate':1e-2,
'batch_size':8,
'adjust_lr':True,
'do_augmentation':True,
'augment_parameters':[0.8, 1.2, 0.5, 2.0, 0.8, 1.2], Here it is the result. Obviously, it should be trained further, however, it is stable with lr=1e-2 and batch size 8. |
Thank you @NikolasEnt for the effort of training the model from scratch. I do get perfect disparity map for selected images but it doesn't seem to applies to all of the kitti test images even after training for 17 epoch with same parameters on full kitti dataset.
Is it just me or do you face the same problem? Reconstructed images and corresponding disparities during my training: |
Hi, @alwynmathew. It looks like the second original raw image has some issues. They may be due to video->image transformation process or image encoding in the dataset. Personally, I didn't observe such examples, however, I didn't exam the whole dataset. |
Results with
lr=1e-3
Epoch 1:
Epoch 2:
Epoch 5:
Disparities are degrading as I train more.
The text was updated successfully, but these errors were encountered: