Package | Description |
---|---|
org.deeplearning4j.nn.conf.dropout |
Modifier and Type | Method and Description |
---|---|
Dropout |
Dropout.clone() |
Dropout |
Dropout.helperAllowFallback(boolean allowFallback)
When using a helper (CuDNN or MKLDNN in some cases) and an error is encountered, should fallback to the non-helper implementation be allowed?
If set to false, an exception in the helper will be propagated back to the user.
|
Copyright © 2019. All rights reserved.