Comments (4)
Hi Sander, the default model is not fully-convolutional and as a consequence it's quite expensive (and has too many weights) for large images. In particular, this is likely caused by the cdna
transformations. I'd suggest to try dna
or flow
transformations. This can be done by passing this flag to the train.py
script:
--model_hparams transformation=dna
For the flow transformations, I'd also use some regularization on the flows, e.g.
--model_hparams tv_weight=0.001,transformation=flow
With these hyperparameters, a batch_size
of 1 should not give OOM errors. To train with a batch_size
of 16, you'd need to do multi-GPU training with 4 or 8 GPUs, or reduce the number of expensive layers (e.g. use larger strides, use less layers, only use ConvRNN layers once the features maps are small enough, etc).
from video_prediction.
Hi Alex,
Thanks for you timely Reply. I turn --model_hparams transformation=dna and also batch_size equal to 1 ,But it still have oom error, just extended the running time compare to transformation=cdna, So I want to know why gpu memory increace in train model , if don't have good resolutions, I will reduce the layers etc. Extra information: my Gpu is GeForce GTX 1080 οΌthe gpu have 11GB memory .
I look forward to your reply. Thank you.
Best,
Sander
from video_prediction.
Can you try flow transformation instead? DNA is still a bit computationally and memory intensive given that there is no native efficient implementation of locally connected layers.
from video_prediction.
Thanks a lot .when I use small image and reduce number of feature maps ,it solved. close this issue.
from video_prediction.
Related Issues (20)
- Is downloading dataset necessary for sample prediction videos? HOT 1
- Error in downloading dataset (partially downloaded) HOT 1
- Checkpoint data loss error when evaluating
- Training stability & progress HOT 1
- train with my own dataset
- what is the difference between Bair action free and action conditioned HOT 1
- FailedPreconditionError while trying to predict using gan_only model on KTH
- ValueError: as_list() is not defined on an unknown TensorShape. HOT 6
- Unable to download pretrained model HOT 1
- Using trained model for custom sized images HOT 1
- Questions about evaluation with the deterministic model
- KeyError: 'gen_states' when run train.py
- KL Loss Weight is zero
- The KHT dataset have not existed any more
- File "scripts/generate.py", line 15, in <module> from video_prediction import datasets, models ModuleNotFoundError: No module named 'video_prediction' HOT 1
- Training error HOT 4
- Testing on custom images
- Dependency Nightmare
- bash download pre-trained model gives an error
- CDNA Masks
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from video_prediction.