Comments (4)
Hi,
PRECISE_BN deos not affect the performance in the final model really, it just makes the train/val error curve looks better when you visualize it.
I have also tried using 16 samples per batch, but i actually did not get much improvement in the case of training with 400K iterations.
from video-nonlocal-net.
Thank you for your replay, when I use 16 samples per batch, I can get the performacne in the paper, but 8 samples per batch is 1.5% than 16 samples per batch.
from video-nonlocal-net.
Hi,
In that case, i am actually suspecting your lr schedule might not be well adjusted. If you are using a 4GPUs machine and running with our 8GPU script, remember to adjust the lr by using lr = lr/2 and double the training iterations, with batchsize=8 samples per GPU.
from video-nonlocal-net.
Hi,
ALL training use the same configs(base_lr=0.01 and total training epochs=90), except the batch_size per GPU(8 or 16).
Because I use my own code and pre_train model(not your release code and pre_train model), the config may be not suitable for me? I have try some experiments, expect have a good result.
from video-nonlocal-net.
Related Issues (20)
- Some problem when building with the newest version of caffe2 HOT 1
- No rm & riv in the pretrain model BN layers HOT 1
- Is the code version Python2 or Python3? HOT 1
- Kinetics pre-trained model for resnet 101 backbone?
- Copying pre-trained weights to pytorch model HOT 9
- Why no relu after nonlocal ?
- kinetics datasets HOT 25
- Why did you use the resnet structure instead of the inception structure in i3d? HOT 2
- matrix TWH*TWH
- Questions about GPU memory usage in non local blocks.
- inference for visualizing the relation between different locations and frames
- Did anyone use Nonlocal module on Optical Flow features?
- How to visualize the non-local operation from the input? HOT 1
- Temporal Convolution Selection in bottlenecks
- Error
- How to get caffe2_customized_ops/video compatible with the current official caffe2 repository? HOT 1
- Question about number of parameters
- How to insert a non-local module in Resnet50 or Resnet101?
- Subsampling while maintaining an identity block
- How can i read video from the lmdb database of video?
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 video-nonlocal-net.