-
Notifications
You must be signed in to change notification settings - Fork 6.8k
R-package lr_scheluder, clip_gradient and xavier initializer #1323
Comments
I have to say it is not implemented, although I don't want to. Any PR will be appreciated. Otherwise, you need to wait until I finish the paper by hand. |
I am relatively competent at R but I don't have the knowledge in ML to implement those, so I'll wait. |
@thirdwing I'm working on this and more will follow |
🍺 Release lr_sheduler, clip_gradient, Xavier initializer for R package. Fix apache#1323. Add name to list as suggested. Ref: PR apache#1554
[R] lr_scheduler, clip_gradient, Xavier initializer are supported for R package. close #1323
In mx.init.Xavier when shape has a length larger than two, fan_in is incorrect because it contains a vector instead of a number and results in an error message: "Error: expecting a single value" |
@Gelu74 Thank you!! Can you send a PR for this? Besides, can you also add an example in https://github.com/dmlc/mxnet/blob/master/doc/R-package/fiveMinutesNeuralNetwork.md ? |
I have seen the PR. Let's wait for the testing. A Kaggle example will be great! If you can provide more details, I think it can also be a blog post (http://dmlc.ml/). |
There is nothing fancy in my kaggle example, it is just a port to R of the python code (which is actually a port from cxxnet) .done by @antinucleon https://github.com/dmlc/mxnet/tree/master/example/kaggle-ndsb1 |
I am trying to port a model from python to R, basically the model call in python is:
model = mx.model.FeedForward(
ctx = dev,
symbol = net,
num_epoch = 35,
learning_rate = 0.01,
momentum = 0.9,
wd = 0.0001,
clip_gradient = 5,
lr_scheduler = mx.lr_scheduler.FactorScheduler(step=epoch_size * lr_factor_epoch, factor = 0.1),
initializer = mx.init.Xavier(factor_type="in", magnitude=2.34))
but I can't find in R the equivalents for lr_scheduler (and mx.lr_scheduler.FactorScheduler) , clip_gradient and mx.init.Xavier.
I guess they have not been implemented in R yet, right?
The text was updated successfully, but these errors were encountered: