Comments (8)
The Flownet2 paper actually recommends to train the networks one at a time, starting with FlowNetC, then fix this, and train FlowNetS1 and so on.
training flownet2 directly on flying-chairs would lead to the type of epe explosion you're getting.
from flownet2-pytorch.
Could you run this command that runs flownetc, and see if you get the same error?
python main.py --batch_size 8 --model FlowNet2C --optimizer=Adam --optimizer_lr=1e-4 --loss=MultiScale --loss_norm=L1
--loss_numScales=5 --loss_startScale=4 --optimizer_lr=1e-4 --crop_size 384 512
--training_dataset FlyingChairs --training_dataset_root /path/to/flying-chairs/dataset
--validation_dataset MpiSintelClean --validation_dataset_root /path/to/mpi-sintel/clean/dataset
from flownet2-pytorch.
@fitsumreda But I just try to train the FlowNetC on FlyingChairs directly, I meet other problems. Could you help me?
from flownet2-pytorch.
It works! I am wondering whether you could provide more details, such as the well trained models by yourself.
from flownet2-pytorch.
@PkuRainBow @fitsumreda Did you get converged result with the mentioned training parameters?
Using python main.py --batch_size 8 --model FlowNet2C --optimizer=Adam --optimizer_lr=1e-4 --loss=MultiScale --loss_norm=L1 \ --validation_frequency 1 \ --loss_numScales=5 --loss_startScale=4 --optimizer_lr=1e-4 --crop_size 384 512 \ --training_dataset FlyingChairs --training_dataset_root /root/per_nas/FlyingChairs_release/data \ --validation_dataset MpiSintelClean --validation_dataset_root /root/MPI-Sintel-complete/training
after 1 epoch (~3 hr in my machine), my training loss curve still keeps jumping.
from flownet2-pytorch.
@dvorak0 Do you get good result on training FlowNet2C? My curve is also bumping seriously while training. Very grateful if you could share your experience. Thanks!
from flownet2-pytorch.
@PkuRainBow hi, have you trained flownet2 successfully by training part of flownet2 first? could you tell me how to freeze parameters?
from flownet2-pytorch.
@MatthewD1993 Hi, have you trained FlowNet2C successfully? My loss curve is also bumping while training. Thanks a lot.
from flownet2-pytorch.
Related Issues (20)
- Flownet2 model for faces HOT 1
- Thanks for this repository! could you please provide the pretrained model for FlowNet2ss or FlowNet2s (lower-case letters, pytorch)? HOT 2
- AttributeError: Module 'time' has no attribute 'clock'
- 想问下如何跑多个文件
- I cannot load the pretrained FlowNetS
- Training with MultiScale loss
- Should I extact "tar" for FlowNet2_checkpoint.pth.tar ?
- Groundtruth of my dataset!!!
- How to achieve the 3D version of correlation layer?
- CUDA error: the provided PTX was compiled with an unsupported toolchain
- start_epoch argument fix
- Error when training Flownet2S HOT 1
- Wrong calculation of EPE HOT 1
- Installation is a nightmare HOT 3
- TypeError: forward() takes 2 positional arguments but 3 were given,flownetc_flow2 = self.flownetc(x)[0].why!!!!
- cuda version HOT 2
- Segmentation fault
- dimension unmatch problem in model
- No module named 'flownet2_models
- What version of pytorch and cuda should I choose
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 flownet2-pytorch.