sandeep-krishnamurthy commented on a change in pull request #12498: Code
modification for testcases of various network models in directory example
URL: https://github.com/apache/incubator-mxnet/pull/12498#discussion_r226874463
##########
File path: example/bayesian-methods/bdk_demo.py
##########
@@ -180,18 +183,18 @@ def run_mnist_SGLD(training_num=50000):
minibatch_size = 100
net = get_mnist_sym()
data_shape = (minibatch_size,) + X.shape[1::]
- data_inputs = {'data': nd.zeros(data_shape, ctx=dev()),
- 'softmax_label': nd.zeros((minibatch_size,), ctx=dev())}
+ data_inputs = {'data': nd.zeros(data_shape, ctx=dev(xpu)),
+ 'softmax_label': nd.zeros((minibatch_size,), ctx=dev(xpu))}
initializer = mx.init.Xavier(factor_type="in", magnitude=2.34)
- exe, sample_pool = SGLD(sym=net, dev=dev(), data_inputs=data_inputs, X=X,
Y=Y,
+ exe, sample_pool = SGLD(sym=net, dev=dev(xpu), data_inputs=data_inputs,
X=X, Y=Y,
X_test=X_test, Y_test=Y_test,
total_iter_num=1000000,
initializer=initializer,
learning_rate=4E-6, prior_precision=1.0,
minibatch_size=100,
thin_interval=100, burn_in_iter_num=1000)
-def run_mnist_DistilledSGLD(training_num=50000):
+def run_mnist_DistilledSGLD(training_num=50000, xpu=0):
Review comment:
This means, by default, mx.gpu(0). Should it default to CPU instead by
making xpu=None?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
