Comments (12)
Setting train/epoch to 0 in data/model/dcrnn_test_config.yaml solves the problem for me.
from dcrnn_pytorch.
@chnsh actually I ended up doing the change in data/model/pretrained/METR-LA/config.yaml and that did it
from dcrnn_pytorch.
@zhenhuascut @victorsoda
"'models/epo64.tar' " is not provided in this branch........
from dcrnn_pytorch.
Thanks, I have solved it.
from dcrnn_pytorch.
Still don't see epo64.tar ... It would be great if you could upload it. Many thanks!
from dcrnn_pytorch.
Still don't see too... Would you upload it then I could reproduce your work? Thanks a lot.
from dcrnn_pytorch.
I also got the same trouble, but at 51 epoch. Can you help me solve it? Thanks a lot.
from dcrnn_pytorch.
Setting train/epoch to 0 in data/model/dcrnn_test_config.yaml solves the problem.
Thanks! I tried successfully.
from dcrnn_pytorch.
Hi everyone, I am sorry I have been unable to reply - @htn274 is correct - the epoch is intended to be the checkpoint from where to resume and I have since then shut down the server (I am a poor student 🥼) and haven't been able to retrieve the weights at epoch 64 - if you just set it to 0 and train, you will be able to reproduce the results
from dcrnn_pytorch.
I don't believe setting train/epoch to 0 is a solution for this problem. As you train the model by the code, the trained models are saved as models/epo0.tar, epo1.tar,... etc. Therefore if you run "run_demo" with train/epoch = 0, it means you run demo with the trained model only with the first epoch. So I ask you to add the best model (epoXX.tar) at the models/ for METR-LA, and PEMS-BAY then we can test with these models
from dcrnn_pytorch.
@semink that is incorrect - the model only tries to load existing weights if epoch > 0, so by setting epoch=0 will do the job as @baosws helpfully pointed out.
I am closing this issue for now - the solution is to train it and once it has trained, set the correct epoch number in config.yml and that should work
from dcrnn_pytorch.
@chnsh this didn't work for me. I still get the same error
from dcrnn_pytorch.
Related Issues (20)
- PEMS-BAY HOT 4
- A problem in gcrnn_train_pytorch
- Double sigmoid inside RNNCell HOT 4
- About the function "_setup_graph()” HOT 1
- The formulation of Diffusion Convolution is wrong HOT 1
- About Missing Data (0 values)
- Test error calculation is not correct HOT 1
- Why are some speed data negative?
- Node connectivity or sensors interaction
- Figure generation HOT 2
- How where the figures generated? HOT 1
- Run the Pre-trained Model on METR-LA
- it doesn't seem to improve in the test run
- Problem with curriculum learning?
- Testing results during training HOT 7
- Lr scheduler resets when resuming model HOT 1
- CUDA out of memory error HOT 1
- Using no convolution better than DCRNN paper result? HOT 1
- Where is the resulting graph of the program running HOT 5
- About the performance improvement compared with Tensorflow implementation HOT 3
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 dcrnn_pytorch.