NoAvailableBackendException: Please ensure that you have an nd4j backend on your classpath

NoAvailableBackendException

Exception in thread "main" java.lang.ExceptionInInitializerError
	at org.deeplearning4j.nn.conf.NeuralNetConfiguration$Builder.seed(NeuralNetConfiguration.java:671)
	at Trainer.TrainerImpl.main(TrainerImpl.java:54)
Caused by: java.lang.RuntimeException: org.nd4j.linalg.factory.Nd4jBackend$NoAvailableBackendException: Please ensure that you have an nd4j backend on your classpath. Please see: http://nd4j.org/getstarted.html
	at org.nd4j.linalg.factory.Nd4j.initContext(Nd4j.java:5768)
	at org.nd4j.linalg.factory.Nd4j.<clinit>(Nd4j.java:202)
	... 2 more
Caused by: org.nd4j.linalg.factory.Nd4jBackend$NoAvailableBackendException: Please ensure that you have an nd4j backend on your classpath. Please see: http://nd4j.org/getstarted.html
	at org.nd4j.linalg.factory.Nd4jBackend.load(Nd4jBackend.java:213)
	at org.nd4j.linalg.factory.Nd4j.initContext(Nd4j.java:5765)
	... 3 more

pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
	<modelVersion>4.0.0</modelVersion>
	<properties>
		<maven.compiler.source>1.8</maven.compiler.source>
		<maven.compiler.target>1.8</maven.compiler.target>
		<slf4j.version>1.7.21</slf4j.version>
		<spark.version>2.1.0</spark.version>
		<guava.version>23.0</guava.version>
		<jfreechart.version>1.0.19</jfreechart.version>
	</properties>

	<parent>
		<groupId>Crypto</groupId>
		<artifactId>Trader</artifactId>
		<version>0.0.1-SNAPSHOT</version>
	</parent>

	<artifactId>primary-source</artifactId>
	<packaging>jar</packaging>

	<name>core project classes</name>

	<repositories>
		<repository>
			<id>jitpack.io</id>
			<url>https://jitpack.io</url>
		</repository>
	</repositories>

	<dependencies>
		<dependency>
			<groupId>org.deeplearning4j</groupId>
			<artifactId>deeplearning4j-core</artifactId>
			<version>1.0.0-beta4</version>
		</dependency>
		<dependency>
			<groupId>org.nd4j</groupId>
			<artifactId>nd4j-cuda-9.2-platform</artifactId>
			<version>1.0.0-beta4</version>
		</dependency>
		<!--dependency>
			<groupId>org.nd4j</groupId>
			<artifactId>nd4j-native-platform</artifactId>
			<version>1.0.0-beta4</version>
		</dependency-->
		<dependency>
			<groupId>org.deeplearning4j</groupId>
			<artifactId>deeplearning4j-cuda-9.2</artifactId>
			<version>1.0.0-beta4</version>
		</dependency>
		<dependency>
			<groupId>org.datavec</groupId>
			<artifactId>datavec-jdbc</artifactId>
			<version>1.0.0-beta4</version>
		</dependency>

		<dependency>
			<groupId>me.joshmcfarlin</groupId>
			<artifactId>CryptoCompareAPI</artifactId>
			<version>master-SNAPSHOT</version>
		</dependency>
		<dependency>
			<groupId>com.github.jeffreytai</groupId>
			<artifactId>cryptocompare-api-wrapper</artifactId>
			<version>1.0.0</version>
		</dependency>
		<!-- https://mvnrepository.com/artifact/org.springframework/spring-web -->
		<dependency>
			<groupId>org.springframework</groupId>
			<artifactId>spring-web</artifactId>
			<version>5.1.8.RELEASE</version>
		</dependency>
		<!-- https://mvnrepository.com/artifact/com.fasterxml.jackson.core/jackson-databind -->
		<dependency>
			<groupId>com.fasterxml.jackson.core</groupId>
			<artifactId>jackson-databind</artifactId>
			<version>2.9.9.1</version>
		</dependency>

		<dependency>
			<groupId>com.squareup.retrofit2</groupId>
			<artifactId>retrofit</artifactId>
			<version>2.5.0</version>
		</dependency>

		<dependency>
			<groupId>com.squareup.retrofit2</groupId>
			<artifactId>converter-jackson</artifactId>
			<version>2.5.0</version>
		</dependency>

		<dependency>
			<groupId>org.apache.spark</groupId>
			<artifactId>spark-sql_2.10</artifactId>
			<version>${spark.version}</version>
			<exclusions>
				<exclusion>
					<groupId>org.slf4j</groupId>
					<artifactId>slf4j-log4j12</artifactId>
				</exclusion>
			</exclusions>
		</dependency>
		<dependency>
			<groupId>org.apache.spark</groupId>
			<artifactId>spark-mllib_2.10</artifactId>
			<version>${spark.version}</version>
			<exclusions>
				<exclusion>
					<groupId>org.slf4j</groupId>
					<artifactId>slf4j-log4j12</artifactId>
				</exclusion>
			</exclusions>
		</dependency>
		<dependency>
			<groupId>org.apache.spark</groupId>
			<artifactId>spark-core_2.10</artifactId>
			<version>${spark.version}</version>
			<exclusions>
				<exclusion>
					<groupId>org.slf4j</groupId>
					<artifactId>slf4j-log4j12</artifactId>
				</exclusion>
			</exclusions>
		</dependency>
		<dependency>
			<groupId>org.jfree</groupId>
			<artifactId>jfreechart</artifactId>
			<version>${jfreechart.version}</version>
		</dependency>
		<!-- Guava dependency -->
		<dependency>
			<groupId>com.google.guava</groupId>
			<artifactId>guava</artifactId>
			<version>${guava.version}</version>
		</dependency>
	</dependencies>

	<build>
		<plugins>
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-javadoc-plugin</artifactId>
				<configuration>
					<minmemory>128m</minmemory>
					<maxmemory>512m</maxmemory>
				</configuration>
			</plugin>
		</plugins>
	</build>
</project>

RIP

Manually looked for the latest driver for the GTX 460 on the NVIDIA website. 391.35 is actually the last one from march 2018. Downloaded and installed it anyway. Also cleaned out the .javacpp folder in the user directory, which had some related stuff in it. Driver DLL version in CUDA-Z showed exactly the same version as before. In the end the same error occurs:

Time for some meditation before the computer goes flying out of the window.

Compiling with Java 8 instead of Java 7: doesn't help.

I think there is my problem. The cuda driver is throwing errors. Guess I was under the false impression that CUDA-Z means everything is fine with the driver. Apparently the driver is too old but because there is no newer one Guess I will need to switch to an even older cuda then 9.2.

Downgrading to cuda 8.0 did the trick. But now ND4J just straight up tells me: CUDA backend requires compute capatibility of 3.0 and above to run.

Card is simply too old. I'll play around with downgrading cuda as well, because after all this time i would like to see it actually run something.. probably slower then the CPU anyway.