Comments (13)
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.
Full Kitti dataset from the original repo was utilized for training.
from monodepth-pytorch.
Hello, @alwynmathew!
What data and hyperparameters do you use for training?
I'd like to reproduce the issue.
from monodepth-pytorch.
I used exact same data and hyperparameters you have used in the demo notebook.
from monodepth-pytorch.
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).
from monodepth-pytorch.
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?
from monodepth-pytorch.
lr=1e-2; batch=20 is good enough (see above) for our implementation
from monodepth-pytorch.
@NikolasEnt batch_size
= 20 is too big.
Epoch 10 with batch_size
= 8 and lr=1e-2
Epoch 16
Its still unstable.
from monodepth-pytorch.
Hello, @alwynmathew!
Once again. Are you sure you downloaded correct dataset as described here?
Because there are 38237 images and you attached your results for the first 10 epochs after approximately an hour after @NikolasEnt answered you about lr. And you used smaller batch size what means that you will need more time for training than we do while we needed something about 45 minutes for 1 epoch using single GTX1080 Ti. It looks like something wrong with your data or equipment.
During this week we will try to reproduce our training using exactly this repo without any changes downloaded on new machine and publish disparities we get after 10 epochs in this thread.
from monodepth-pytorch.
Hi @Sparkling-Brick, according to the notebook provided in the repo, the data loader is just loading from one of the kitti dataset subfolder 'data_dir':'../../2011_09_26/'
.
from monodepth-pytorch.
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.
Moreover if you read our README you would notice the structure of data and path variable are described here.
from monodepth-pytorch.
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?
from monodepth-pytorch.
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.
'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]
Is it just me or do you face the same problem?
Reconstructed images and corresponding disparities during my training:
from monodepth-pytorch.
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.
Ideally, such images should be excluded from train/val subsets.
from monodepth-pytorch.
Related Issues (20)
- This code is able to reproduce similar results to those in the original paper HOT 16
- RMSE keeps increasing after 25 epochs training while disparity prediction looks fine
- Question about how to get the original image HOT 1
- How do you compute L-R Consistency HOT 1
- Difference between ResNet50_md and ResNet model
- why the disp_gradient_loss, lr_loss is zero and the total loss is not getting converging?
- test my data HOT 2
- How can I get deep information? HOT 2
- disparity map error HOT 1
- [Question] How to get the metric disparity value? HOT 3
- [Feature requested] Support for depth-separable(depth-wise) backbones such as MobileNetV2, EfficientNet... HOT 1
- Can anyone provide the download URL of pretrained model 'monodepth_resnet18_001_cpt.pth' in this repository? HOT 6
- Why horizontal flip HOT 1
- Key already registered with the same priority: GroupSpatialSoftmax HOT 1
- Does this work on stereo image pair (not video) HOT 3
- How to interpolate the sparse gt depth map? HOT 1
- What is the loss value of the trained model? HOT 1
- Training data with monocular HOT 1
- datasets HOT 1
- How can I generate depth maps for other image datasets using the code here?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from monodepth-pytorch.