-
Notifications
You must be signed in to change notification settings - Fork 11
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
Finetune the ConvNeXt-L on KITTI #26
Comments
Did you load a pre-trained model (self-supervised pre-trained), and what's your SSL scores. |
Thank you for your reply! Yes, I load a pre-trained model trained with script train.py with 20 epochs. What is SSL score? The training loss score is around 0.3~0.4, and the validation silog is 7.467. |
I mean, what's your SSL model's metrics, AbsRel, RMSE, etc. |
AbsRel |
Em, AbsRel = ?, I mean your SSL model's evaluation results on KITTI, not SiLog loss |
The SSL model’s ecaluation results on KITTI are: abs_rel: 0.060, rmse: 2.642. |
That's interesting, you got better SSL scores but worse SSL+Sup scores. |
Can you provide your fine-tuning args? I think you should choose a much smaller learning_rate. |
--name cvnXt_075_1130 |
I recommend --bs 16 and I think lr should be smaller, 1e-6, 5e-6, etc. |
Thanks! I will try. |
Hi @FangjunWang, I am very excited to reproduce ConvNetX results as well. However, I am currently stuck on the first stage (SSL training). I ran the training using the following command: in cvnXt_L_320x1024.txt I changed only data_path, log_dir and batch_size=8 (instead of 16 as original, as I understood you did same change). Should I download pretrained PoseNet or other weights, or maybe I calculates the metrics in the wrong way (but I checked it on downloaded resnet model and it reproduce same score as @hisfog claimed in gitrepo). |
Hello, my parameters are: I did not change any other things besides above parameters. Hope this helps! |
@FangjunWang, thank you for quick response. I have the same parameters. also did you do something else? download some pretrained weights before training or pretrained PoseNet? |
Yes, I trained and evaluated the model use the same command. |
@FangjunWang, for this you should change params to: |
I changed networks/Unet.py like this: |
@FangjunWang, thanks. |
@FangjunWang, I have tried convnext_large_22k_1k_224 as you suggest it provides slightly better results, however situation is similar. But for convnext I found next situation it improves first 6-9 epochs, and after that not improve but get worse and worse. |
@Lavreniuk here is my parameters: --data_path /mnt/RG/dataset/kitti_data |
hi, @jerry-ryu , I have not reproduced the result of original repo, especially with much better result that was mentioned. I think you should train without pretrained posenet, but maybe I am wrong. |
Apologies for the delayed response, For reproducing results on KITTI,please DO NOT use the latest code release (I'm not sure what may cause these issues above). Instead, you can kindly utilize the following version by git checkout 6a1e997f97caef8de080bb2873f71cfbad9a8047 which is consistent with the implementation of paper SQLdepth, without any additional modifications. |
@Lavreniuk @hisfog |
@hisfog I will post my experimental results and argsfiles for those who want to train SQLdepth. ResNet50 320x1024-args:
ConvNext 192x640(Due to lack of gpu capacity, 192x640 was used instead of 320x1024)
Thank you again for your wonderful code and congratulations paper accept! p.s. |
Thank you @hisfog and @jerry-ryu for the kind responses and sharing the experiment settings. Background: I was in the same situation where I couldn't get the similar results to the numbers reported in the paper when using the latest code. Now knowing this issue, I'm training with the suggested branch, but curious what caused the difference in my result. I checked the differences between the latest commit and 6a1e997, and the most notable difference I can find was the filename changes in |
@NoelShin |
hello!I notice that too.Do you know which paper the old split came from? |
Hello and nice work! My question is how to finetune the model on KITTI?
I tried with the script ./finetune/train_ft_SQLdepth.py but cannot get good enough results. Only abs_rel 0.0494 and rmse 2.182.
The text was updated successfully, but these errors were encountered: