-
Keras v. 1.2.2
dl4j 0.8.0
Tried making conv net as in this gist:
https://gist.github.com/jef5ez/fbe9e181c7132078d4f3a0855801be80
The dl4j model does not produce the same outputs and required t…
-
[####] Issue Description
OutOfMemoryException after some hours when repeating DL4J-runs (from data reading and parsing into DataSets, to splitting, training and testing).
Pom, Code, Stacktrace i…
JZ051 updated
5 years ago
-
To go from "masked RNN labels with only one time step present" format (as used in RnnOutputLayer) to 2D format (as used in OutputLayer)
-
Test:
```java
@Test
public void testFromNumpy() {
INDArray out = Nd4j.createFromNpyFile(new File("./error2.npy"));
System.out.println(ArrayUtil.toList(ArrayUtil.toInts(out.shape())));
…
rnett updated
5 years ago
-
#### Issue Description
Hello, I am studying DL4J embedding layers and I have a question about the length of input sequences. In Keras (sorry for the cross-referencing), we can do this:
inpu…
ghost updated
5 years ago
-
#### Issue Description
Yay! DL4J has a new model zoo. However, there's still much to do.
@tomthetrainer I'm going to do a first pass at the DL4J website and then update the examples that could u…
-
Probably introduced by other changes recently. Only one of many cases failing for each of these 3 tests.
![image](https://user-images.githubusercontent.com/2360237/55548233-c1965100-571e-11e9-83f5-…
-
Using:
> ```
> 0.4-rc3.6
> 0.4-rc3.8"
> ```
I ran into issue https://github.com/deeplearning4j/deeplearning4j/issues/846, still seen last month by lhyan792 in glitter. Since this h…
-
---------------------------
[INFO] -----------< org.deeplearning4j:dl4j-cuda-specific-examples >-----------
[INFO] Building DeepLearning4j CUDA special examples 1.0.0-beta4 [7/10]
[INFO] --…
-
DL4J has:
```
case "Nadam": {
double lr = (double) optimizerParameters.get("lr");
double beta1 = (double) optimizerParameters.get("beta_1");
doubl…
dkull updated
5 years ago