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

Example 16 with TensorArray

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

the class L1NormalizationLayer method eval.

@Nonnull
@Override
public Result eval(@Nonnull final Result... input) {
    Arrays.stream(input).forEach(nnResult -> nnResult.addRef());
    final Result in = input[0];
    final TensorList inData = in.getData();
    inData.addRef();
    return new Result(TensorArray.wrap(IntStream.range(0, inData.length()).mapToObj(dataIndex -> {
        @Nullable final Tensor value = inData.get(dataIndex);
        try {
            final double sum = value.sum();
            if (!Double.isFinite(sum) || 0 == sum) {
                value.addRef();
                return value;
            } else {
                return value.scale(1.0 / sum);
            }
        } finally {
            value.freeRef();
        }
    }).toArray(i -> new Tensor[i])), (@Nonnull final DeltaSet<Layer> buffer, @Nonnull final TensorList outDelta) -> {
        if (in.isAlive()) {
            final Tensor[] passbackArray = IntStream.range(0, outDelta.length()).mapToObj(dataIndex -> {
                Tensor inputTensor = inData.get(dataIndex);
                @Nullable final double[] value = inputTensor.getData();
                Tensor outputTensor = outDelta.get(dataIndex);
                @Nullable final double[] delta = outputTensor.getData();
                final double dot = ArrayUtil.dot(value, delta);
                final double sum = Arrays.stream(value).sum();
                @Nonnull final Tensor passback = new Tensor(outputTensor.getDimensions());
                @Nullable final double[] passbackData = passback.getData();
                if (0 != sum || Double.isFinite(sum)) {
                    for (int i = 0; i < value.length; i++) {
                        passbackData[i] = (delta[i] - dot / sum) / sum;
                    }
                }
                outputTensor.freeRef();
                inputTensor.freeRef();
                return passback;
            }).toArray(i -> new Tensor[i]);
            assert Arrays.stream(passbackArray).flatMapToDouble(x -> Arrays.stream(x.getData())).allMatch(v -> Double.isFinite(v));
            @Nonnull TensorArray tensorArray = TensorArray.wrap(passbackArray);
            in.accumulate(buffer, tensorArray);
        }
    }) {

        @Override
        protected void _free() {
            inData.freeRef();
            Arrays.stream(input).forEach(nnResult -> nnResult.freeRef());
        }

        @Override
        public boolean isAlive() {
            return in.isAlive();
        }
    };
}

Example 17 with TensorArray

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

the class SingleDerivativeTester method testUnFrozen.

/**
 * Test un frozen.
 *
 * @param component      the component
 * @param inputPrototype the input prototype
 */
public void testUnFrozen(@Nonnull final Layer component, Tensor[] inputPrototype) {
    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().setFrozen(false);
    List<TensorArray> inputCopies = Arrays.stream(inputPrototype).map(TensorArray::wrap).collect(Collectors.toList());
    Result[] inputs = inputCopies.stream().map(tensor -> new Result(tensor, (@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(inputs);
    } finally {
        for (@Nonnull Result result : inputs) {
            result.freeRef();
        }
        for (@Nonnull TensorArray tensorArray : inputCopies) {
            tensorArray.freeRef();
        }
    }
    @Nonnull final DeltaSet<Layer> buffer = new DeltaSet<Layer>();
    TensorList tensorList = eval.getData();
    eval.accumulate(buffer, tensorList);
    eval.freeRef();
    @Nullable final List<double[]> stateList = frozen.state();
    final List<Delta<Layer>> deltas = stateList.stream().map(doubles -> {
        return buffer.stream().filter(x -> x.target == doubles).findFirst().orElse(null);
    }).filter(x -> x != null).collect(Collectors.toList());
    if (deltas.isEmpty() && !stateList.isEmpty()) {
        throw new AssertionError("Nonfrozen component not listed in delta. Deltas: " + deltas);
    }
    frozen.freeRef();
    buffer.freeRef();
    if (!reachedInputFeedback.get() && inputPrototype.length != 0) {
        throw new RuntimeException("Nonfrozen component did not pass input backwards");
    }
}

Example 18 with TensorArray

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

the class ObjectLocation method renderAlpha.

/**
 * Render alpha tensor.
 *
 * @param alphaPower     the alpha power
 * @param img            the img
 * @param locationResult the location result
 * @param classification the classification
 * @param category       the category
 * @return the tensor
 */
public Tensor renderAlpha(final double alphaPower, final Tensor img, final Result locationResult, final Tensor classification, final int category) {
    TensorArray tensorArray = TensorArray.wrap(new Tensor(classification.getDimensions()).set(category, 1));
    DeltaSet<Layer> deltaSet = new DeltaSet<>();
    locationResult.accumulate(deltaSet, tensorArray);
    double[] rawDelta = deltaSet.getMap().entrySet().stream().filter(x -> x.getValue().target == img.getData()).findAny().get().getValue().getDelta();
    Tensor deltaColor = new Tensor(rawDelta, img.getDimensions()).mapAndFree(x -> Math.abs(x));
    Tensor delta1d = blur(reduce(deltaColor), 3);
    return TestUtil.normalizeBands(TestUtil.normalizeBands(delta1d, 1).mapAndFree(x -> Math.pow(x, alphaPower)));
}

Example 19 with TensorArray

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

the class PerformanceTester method testPerformance.

/**
 * Test learning performance double statistics.
 *
 * @param component      the component
 * @param inputPrototype the input prototype
 * @return the double statistics
 */
@Nonnull
protected Tuple2<Double, Double> testPerformance(@Nonnull final Layer component, final Tensor... inputPrototype) {
    final Tensor[][] data = IntStream.range(0, batches).mapToObj(x -> x).flatMap(x -> Stream.<Tensor[]>of(inputPrototype)).toArray(i -> new Tensor[i][]);
    @Nonnull TimedResult<Result> timedEval = TimedResult.time(() -> {
        Result[] input = ConstantResult.batchResultArray(data);
        @Nullable Result result;
        try {
            result = component.eval(input);
        } finally {
            for (@Nonnull Result nnResult : input) {
                nnResult.freeRef();
                nnResult.getData().freeRef();
            }
        }
        return result;
    });
    final Result result = timedEval.result;
    @Nonnull final DeltaSet<Layer> buffer = new DeltaSet<Layer>();
    try {
        long timedBackprop = TimedResult.time(() -> {
            @Nonnull TensorArray tensorArray = TensorArray.wrap(result.getData().stream().map(x -> {
                return x.mapAndFree(v -> 1.0);
            }).toArray(i -> new Tensor[i]));
            result.accumulate(buffer, tensorArray);
            assert tensorArray.currentRefCount() == 0;
            return buffer;
        }).timeNanos;
        return new Tuple2<>(timedEval.timeNanos / 1e9, timedBackprop / 1e9);
    } finally {
        buffer.freeRef();
        result.freeRef();
        result.getData().freeRef();
    }
}

Example 20 with TensorArray

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

the class BatchDerivativeTester 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>();
        @Nonnull final Tensor data = new Tensor(outputPrototype.getDimensions()).set((k) -> k == j_ ? 1 : 0);
        @Nullable final Result eval = component.eval(ConstantResult.singleResultArray(new Tensor[][] { inputPrototype }));
        eval.getData().get(0);
        @Nonnull TensorArray tensorArray = TensorArray.wrap(data);
        eval.accumulate(buffer, tensorArray);
        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]);
            }
        }
    }
    return gradient;
}