Comments (14)
Code is correct. We are working on the paper update :)
from nvcaffe.
@borisgin Another miss match.
In https://github.com/borisgin/nvcaffe-0.16/blob/caffe-0.16/models/bvlc_alexnet/solver_8K.prototxt
I found you set rampup_interval: 600
, so the warmup for 8k batchsize is 4 epochs.
But your paper(Table 6) said, warm up is 8 epochs.
Something wrong with the paper?
from nvcaffe.
from nvcaffe.
@borisfom
Maybe another mismatch: wgrad_norm in your code is computed from "g + beta* w"(it is computed after regularization), not exactly the same as paper's "g".
from nvcaffe.
And Maybe weight_decay in "rate = gw_ratio * w_norm / (wgrad_norm + weight_decay * w_norm)" should be global weight_decay * local_decay?
from nvcaffe.
It's interesting idea! How would you tune local decay automatically? In our experiments we used only global weight decay which was fixed.
from nvcaffe.
Thanks. I use fixed local decay. What do you think about the first miss match I mentioned above, please?
from nvcaffe.
For GPU branch, weight update, moment , and regularization are fused in to one kernel. So the Regularize() function skips this stage.
from nvcaffe.
wow,I didn't notice that. Thanks
from nvcaffe.
hi @borisgin , Did you use any auto local decay when training ImageNet, along with LARS solver? I found auto local decay feature in your code, But no any clue in the paper. Thanks
from nvcaffe.
My branch has a lot of experimental knobs which I don’t put into official nvcaffe branch since they did not prove themselves yet . Also some features were developed after we submitted paper :). Code supports both momentum and weight decay adjustment policies (currently this is only “poly” or “fixed”) which I used for my experiments with Neumann optimizer
from nvcaffe.
@borisgin How is your experiments with Neumann optimizer? Can I see the code of Neumann optimizer
from nvcaffe.
I experimented with simplifed Neuman optimizer ( wo external loop) . I found that it behaves very similar to the standard SGD with momentum. So we decided not to add this optimizer to nvidia/caffe
from nvcaffe.
你好,请问在用多卡增大batchsize训练的时候,
这个batchsize大小是多卡总的batchsize还是单卡的batchsize?
from nvcaffe.
Related Issues (6)
- Where is mean_file: "/data/imagenet/imagenet_256x256_mean.binaryproto" HOT 1
- [dead silence] NVcaffe Digit Object Detection With TensorRT GoogleNet dead silence HOT 3
- Documentation on major differences from BVLC/caffe HOT 2
- make: *** [.build_release/lib/libcaffe-nv.so.0.16.4] Error 1 HOT 1
- is the batch_size means global batch_size? HOT 1
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 nvcaffe.