-
#### Issue Description
I am setting up a small test project to quickly reproduce Nd4J tests while tackling some of the code issues in `nd4j.java`. The duplicate code for `CreaeDetached` is an easy f…
-
I'm trying to import Inception v3 from Keras to dl4j.
I managed to import the model from json+h5 by making few small tweaks to latest KerasModel class. However when I feed same data as to Keras's …
rohrl updated
5 years ago
-
Following on from the discussion in slack: Our libnd4j conv2d op weights format depend on the activations input format (NCHW vs. NHWC).
https://github.com/deeplearning4j/deeplearning4j/blob/master/li…
-
One allows rank 1 arrays, the other does not:
https://github.com/deeplearning4j/deeplearning4j/blob/83a8ea4eefbdde4ed5dd7af7f416b5ad44a4b704/nd4j/nd4j-backends/nd4j-api-parent/nd4j-api/src/main/java/o…
-
When i migrate from 0.5.0 to 0.7.0, encounted a exception.My code run on hadoop-cluster(2.6.0-cdh5.5.0) with spark framework.
Exception in thread "main" java.lang.UnsupportedClassVersionError: com/…
-
Currently using beta-2 and there are some tests that need to be commented until beta-3 can be used.
-
#### Issue Description
I was looking for a way to load a pretrained FP16 Resnet50 model and run on CPUs. There is no direct way to do that but a round about way as suggested by @raver119 on gitter ch…
-
Currently, exceptions on lambda layers look like this:
```
Exception in thread "main" org.deeplearning4j.nn.modelimport.keras.exceptions.UnsupportedKerasConfigurationException: Unsupported keras lay…
-
Reported by @Kissy: https://github.com/deeplearning4j/deeplearning4j/issues/6527#issuecomment-427737778
> I reproduce the exception compiling with Keras 2.2.3 and importing with 1.0.0-beta2.
It se…
-
def baseline_model():
model = Sequential()
# 1 - Convolution
model.add(Conv2D(64,(3,3), border_mode='same', input_shape=(48, 48,1)))
model.add(BatchNormalization())
mode…