Examples with TensorArray com.simiacryptus.mindseye.lang.TensorArray used on opensource projects

Example 51 with TensorArray

use of com.simiacryptus.mindseye.lang.TensorArray in project MindsEye by SimiaCryptus.

the class SumReducerLayer method eval.

@Nonnull
@Override
public Result eval(@Nonnull final Result... inObj) {
    Arrays.stream(inObj).forEach(nnResult -> nnResult.addRef());
    Arrays.stream(inObj).forEach(x -> x.getData().addRef());
    return new Result(TensorArray.wrap(IntStream.range(0, inObj[0].getData().length()).parallel().mapToDouble(dataIndex -> {
        double sum = 0;
        for (@Nonnull final Result element : inObj) {
            @Nullable Tensor tensor = element.getData().get(dataIndex);
            @Nullable final double[] input = tensor.getData();
            for (final double element2 : input) {
                sum += element2;
            }
            tensor.freeRef();
        }
        return sum;
    }).mapToObj(x -> new Tensor(new double[] { x }, new int[] { 1 })).toArray(i -> new Tensor[i])), (@Nonnull final DeltaSet<Layer> buffer, @Nonnull final TensorList data) -> {
        for (@Nonnull final Result in_l : inObj) {
            if (in_l.isAlive()) {
                @Nonnull TensorArray tensorArray = TensorArray.wrap(IntStream.range(0, in_l.getData().length()).parallel().mapToObj(dataIndex -> {
                    final double delta = data.get(dataIndex).get(0);
                    @Nonnull final Tensor passback = new Tensor(in_l.getData().getDimensions());
                    for (int i = 0; i < Tensor.length(in_l.getData().getDimensions()); i++) {
                        passback.set(i, delta);
                    }
                    return passback;
                }).toArray(i -> new Tensor[i]));
                in_l.accumulate(buffer, tensorArray);
            }
        }
    }) {

        @Override
        protected void _free() {
            Arrays.stream(inObj).forEach(x -> x.getData().freeRef());
            Arrays.stream(inObj).forEach(nnResult -> nnResult.freeRef());
        }

        @Override
        public boolean isAlive() {
            for (@Nonnull final Result element : inObj) if (element.isAlive()) {
                return true;
            }
            return false;
        }
    };
}

Example 52 with TensorArray

use of com.simiacryptus.mindseye.lang.TensorArray in project MindsEye by SimiaCryptus.

the class SingleDerivativeTester method getLearningGradient.

@Nonnull
private Tensor getLearningGradient(@Nonnull final Layer component, final int layerNum, @Nonnull final Tensor outputPrototype, final Tensor... inputPrototype) {
    component.setFrozen(false);
    final double[] stateArray = component.state().get(layerNum);
    final int stateLen = stateArray.length;
    @Nonnull final Tensor gradient = new Tensor(stateLen, outputPrototype.length());
    for (int j = 0; j < outputPrototype.length(); j++) {
        final int j_ = j;
        @Nonnull final DeltaSet<Layer> buffer = new DeltaSet<Layer>();
        Result[] array = ConstantResult.batchResultArray(new Tensor[][] { inputPrototype });
        @Nullable final Result eval = component.eval(array);
        for (@Nonnull Result result : array) {
            result.getData().freeRef();
            result.freeRef();
        }
        @Nonnull TensorArray tensorArray = TensorArray.wrap(new Tensor(outputPrototype.getDimensions()).set((k) -> k == j_ ? 1 : 0));
        eval.accumulate(buffer, tensorArray);
        eval.getData().freeRef();
        eval.freeRef();
        final DoubleBuffer<Layer> deltaFlushBuffer = buffer.getMap().values().stream().filter(x -> x.target == stateArray).findFirst().orElse(null);
        if (null != deltaFlushBuffer) {
            for (int i = 0; i < stateLen; i++) {
                gradient.set(new int[] { i, j_ }, deltaFlushBuffer.getDelta()[i]);
            }
        }
        buffer.freeRef();
    }
    return gradient;
}

Example 53 with TensorArray

use of com.simiacryptus.mindseye.lang.TensorArray in project MindsEye by SimiaCryptus.

the class SingleDerivativeTester method getFeedbackGradient.

@Nonnull
private Tensor getFeedbackGradient(@Nonnull final Layer component, final int inputIndex, @Nonnull final Tensor outputPrototype, @Nonnull final Tensor... inputPrototype) {
    final Tensor inputTensor = inputPrototype[inputIndex];
    final int inputDims = inputTensor.length();
    @Nonnull final Tensor result = new Tensor(inputDims, outputPrototype.length());
    for (int j = 0; j < outputPrototype.length(); j++) {
        final int j_ = j;
        @Nonnull final PlaceholderLayer<Tensor> inputKey = new PlaceholderLayer<Tensor>(new Tensor(1));
        inputKey.getKey().freeRef();
        final Result[] copyInput = Arrays.stream(inputPrototype).map(x -> new Result(TensorArray.create(x), (@Nonnull final DeltaSet<Layer> buffer, @Nonnull final TensorList data) -> {
        }) {

            @Override
            public boolean isAlive() {
                return false;
            }
        }).toArray(i -> new Result[i]);
        copyInput[inputIndex].getData().freeRef();
        copyInput[inputIndex].freeRef();
        double[] target = new double[inputDims * outputPrototype.length()];
        copyInput[inputIndex] = new Result(TensorArray.create(inputTensor), (@Nonnull final DeltaSet<Layer> buffer, @Nonnull final TensorList data) -> {
            if (1 != data.length())
                throw new AssertionError();
            if (data.length() != 1)
                throw new AssertionError();
            @Nonnull final Tensor gradientBuffer = new Tensor(inputDims, outputPrototype.length());
            if (!Arrays.equals(inputTensor.getDimensions(), data.getDimensions())) {
                throw new AssertionError();
            }
            IntStream.range(0, data.length()).forEach(dataIndex -> {
                for (int i = 0; i < inputDims; i++) {
                    @Nullable Tensor tensor = data.get(dataIndex);
                    gradientBuffer.set(new int[] { i, j_ }, tensor.getData()[i]);
                    tensor.freeRef();
                }
            });
            buffer.get(inputKey, target).addInPlace(gradientBuffer.getData()).freeRef();
            gradientBuffer.freeRef();
        }) {

            @Override
            public boolean isAlive() {
                return true;
            }
        };
        @Nullable final Result eval;
        try {
            eval = component.eval(copyInput);
        } finally {
            for (@Nonnull Result nnResult : copyInput) {
                nnResult.freeRef();
                nnResult.getData().freeRef();
            }
        }
        @Nonnull final DeltaSet<Layer> deltaSet = new DeltaSet<Layer>();
        @Nonnull TensorArray tensorArray = TensorArray.wrap(new Tensor(outputPrototype.getDimensions()).set(j, 1));
        try {
            eval.accumulate(deltaSet, tensorArray);
            final Delta<Layer> inputDelta = deltaSet.getMap().get(inputKey);
            if (null != inputDelta) {
                @Nonnull Tensor tensor = new Tensor(inputDelta.getDelta(), result.getDimensions());
                result.addInPlace(tensor);
                tensor.freeRef();
            }
        } finally {
            eval.getData().freeRef();
            eval.freeRef();
            deltaSet.freeRef();
            inputKey.freeRef();
        }
    }
    return result;
}

Example 54 with TensorArray

use of com.simiacryptus.mindseye.lang.TensorArray in project MindsEye by SimiaCryptus.

the class SingleDerivativeTester method testFrozen.

/**
 * Test frozen.
 *
 * @param component      the component
 * @param inputPrototype the input prototype
 */
public void testFrozen(@Nonnull final Layer component, @Nonnull Tensor[] inputPrototype) {
    final int inElements = Arrays.stream(inputPrototype).mapToInt(x -> x.length()).sum();
    inputPrototype = Arrays.stream(inputPrototype).map(tensor -> tensor.copy()).toArray(i -> new Tensor[i]);
    @Nonnull final AtomicBoolean reachedInputFeedback = new AtomicBoolean(false);
    @Nonnull final Layer frozen = component.copy().freeze();
    List<TensorArray> inputCopies = Arrays.stream(inputPrototype).map(TensorArray::wrap).collect(Collectors.toList());
    Result[] input = inputCopies.stream().map((tensorArray) -> new Result(tensorArray, (@Nonnull final DeltaSet<Layer> buffer, @Nonnull final TensorList data) -> {
        reachedInputFeedback.set(true);
    }) {

        @Override
        public boolean isAlive() {
            return true;
        }
    }).toArray(i -> new Result[i]);
    @Nullable final Result eval;
    try {
        eval = frozen.eval(input);
    } finally {
        for (@Nonnull Result result : input) {
            result.freeRef();
        }
        frozen.freeRef();
        for (@Nonnull TensorArray tensorArray : inputCopies) {
            tensorArray.freeRef();
        }
    }
    @Nonnull final DeltaSet<Layer> buffer;
    TensorList tensorList;
    TensorList evalData = eval.getData();
    try {
        buffer = new DeltaSet<Layer>();
        tensorList = evalData.copy();
        eval.accumulate(buffer, tensorList);
    } finally {
        evalData.freeRef();
        eval.freeRef();
    }
    final List<Delta<Layer>> deltas = component.state().stream().map(doubles -> {
        return buffer.stream().filter(x -> x.target == doubles).findFirst().orElse(null);
    }).filter(x -> x != null).collect(Collectors.toList());
    buffer.freeRef();
    if (!deltas.isEmpty() && !component.state().isEmpty()) {
        throw new AssertionError("Frozen component listed in delta. Deltas: " + deltas);
    }
    if (!reachedInputFeedback.get() && 0 < inElements) {
        throw new RuntimeException("Frozen component did not pass input backwards");
    }
}