-
Hi there, I am trying to use your notebook to train on my own dataset. The dataset consists of samples where each sample consists of a single image pair and their respective ground truth flow.
I have…
-
I test the disparity with a warping operation, but it is not correct when directly using the GT disparity, but is correct when using 32xdisp. Is there a scale factor between RGB image and disparity?
-
Hi,
I'm trying to train the model according to the readme, however I'm getting the following error:
python main.py --batch_size 8 --model FlowNet2 --loss=L1Loss --optimizer=Adam --optimizer_lr=…
-
When I run "python main.py", I got the following error. Any pointers to fix it?
My system is pytorch 0.4 , cuda 9.0
Initializing Adam Optimizer
[0.001s] amsgrad = False ()
[0.001s] weigh…
3togo updated
3 years ago
-
Hi, @daigo0927 thank you for your decent implementation of the TF version. It was fun playing with it.
However, I noticed that with your pre-trained Sintel checkpoints. It tends to produce Chess Bo…
-
##### System information (version)
- OpenCV => 4.1.1
- Operating System / Platform => Ubuntu 18.04
- Compiler => gcc 7.5.0
##### Detailed description
Tried to run nvidia optical flow from Ope…
-
Hi~I tried to train flownet2 using MPI-Sintel dataset,but I got such errors and can't make it.
My env is:
cuda10 pytorch1.1.0 python3 ubuntu18
And I had successfully done inference using model …
-
# Bug Report
onnx.shape_inference.infer_shapes is invalid. The program exit automatically.
### System information
- OS Platform and Distribution: Windows 10
- ONNX version: 1.7.0
- Python…
-
I tried to download revised GT of MPI sintel. however the link refused to connect.
would you check the link still alive?
https://download.visinf.tu-darmstadt.de/data/flyingchairs_occ/occlusions_re…
-
Can you tell me the number of training iterations for finetune on flyings3d after pre training on flyingchairs? Would you like to use s-fine to train 0.5m iterations after flyingchairs 1.2m iterations…