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

Example 26 with Result

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

the class ImgPixelGateLayer method eval.

/**
 * Eval nn result.
 *
 * @param input the input
 * @param gate  the gate
 * @return the nn result
 */
@Nonnull
public Result eval(@Nonnull final Result input, @Nonnull final Result gate) {
    final TensorList inputData = input.getData();
    final TensorList gateData = gate.getData();
    inputData.addRef();
    input.addRef();
    gate.addRef();
    gateData.addRef();
    int[] inputDims = inputData.getDimensions();
    assert 3 == inputDims.length;
    return new Result(TensorArray.wrap(IntStream.range(0, inputData.length()).mapToObj(i -> {
        Tensor inputTensor = inputData.get(i);
        Tensor gateTensor = gateData.get(i);
        Tensor result = new Tensor(inputDims[0], inputDims[1], 1).setByCoord(c -> {
            return IntStream.range(0, inputDims[2]).mapToDouble(b -> {
                int[] coords = c.getCoords();
                return inputTensor.get(coords[0], coords[1], b) * gateTensor.get(coords[0], coords[1], 0);
            }).sum();
        });
        inputTensor.freeRef();
        gateTensor.freeRef();
        return result;
    }).toArray(i -> new Tensor[i])), (@Nonnull final DeltaSet<Layer> buffer, @Nonnull final TensorList delta) -> {
        if (input.isAlive()) {
            @Nonnull TensorArray tensorArray = TensorArray.wrap(IntStream.range(0, delta.length()).mapToObj(i -> {
                Tensor deltaTensor = delta.get(i);
                Tensor gateTensor = gateData.get(i);
                Tensor result = new Tensor(input.getData().getDimensions()).setByCoord(c -> {
                    int[] coords = c.getCoords();
                    return deltaTensor.get(coords[0], coords[1], 0) * gateTensor.get(coords[0], coords[1], 0);
                });
                deltaTensor.freeRef();
                gateTensor.freeRef();
                return result;
            }).toArray(i -> new Tensor[i]));
            input.accumulate(buffer, tensorArray);
        }
        if (gate.isAlive()) {
            @Nonnull TensorArray tensorArray = TensorArray.wrap(IntStream.range(0, delta.length()).mapToObj(i -> {
                Tensor deltaTensor = delta.get(i);
                Tensor inputTensor = inputData.get(i);
                Tensor result = new Tensor(gateData.getDimensions()).setByCoord(c -> IntStream.range(0, inputDims[2]).mapToDouble(b -> {
                    int[] coords = c.getCoords();
                    return deltaTensor.get(coords[0], coords[1], 0) * inputTensor.get(coords[0], coords[1], b);
                }).sum());
                deltaTensor.freeRef();
                inputTensor.freeRef();
                return result;
            }).toArray(i -> new Tensor[i]));
            gate.accumulate(buffer, tensorArray);
        }
    }) {

        @Override
        protected void _free() {
            inputData.freeRef();
            input.freeRef();
            gate.freeRef();
            gateData.freeRef();
        }

        @Override
        public boolean isAlive() {
            return input.isAlive() || !isFrozen();
        }
    };
}

Example 27 with Result

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

the class ImgTileAssemblyLayer method eval.

@Nonnull
@Override
public Result eval(@Nonnull final Result... inObj) {
    Arrays.stream(inObj).forEach(nnResult -> nnResult.addRef());
    assert 3 == inObj[0].getData().getDimensions().length;
    int[] outputDims = getOutputDims(inObj);
    return new Result(TensorArray.wrap(IntStream.range(0, inObj[0].getData().length()).parallel().mapToObj(dataIndex -> {
        @Nonnull final Tensor outputData = new Tensor(outputDims);
        int totalWidth = 0;
        int totalHeight = 0;
        int inputIndex = 0;
        for (int row = 0; row < rows; row++) {
            int positionX = 0;
            int rowHeight = 0;
            for (int col = 0; col < columns; col++) {
                TensorList tileTensor = inObj[inputIndex].getData();
                int[] tileDimensions = tileTensor.getDimensions();
                rowHeight = Math.max(rowHeight, tileDimensions[1]);
                Tensor inputData = tileTensor.get(dataIndex);
                ImgTileAssemblyLayer.copy(inputData, outputData, positionX, totalHeight);
                inputData.freeRef();
                positionX += tileDimensions[0];
                inputIndex += 1;
            }
            totalHeight += rowHeight;
            totalWidth = Math.max(totalWidth, positionX);
        }
        return outputData;
    }).toArray(i -> new Tensor[i])), (@Nonnull final DeltaSet<Layer> buffer, @Nonnull final TensorList delta) -> {
        int totalHeight = 0;
        int inputIndex = 0;
        for (int row = 0; row < rows; row++) {
            int positionX = 0;
            int rowHeight = 0;
            for (int col = 0; col < columns; col++) {
                Result in = inObj[inputIndex];
                int[] inputDataDimensions = in.getData().getDimensions();
                rowHeight = Math.max(rowHeight, inputDataDimensions[1]);
                if (in.isAlive()) {
                    int _positionX = positionX;
                    int _totalHeight = totalHeight;
                    @Nonnull TensorArray tensorArray = TensorArray.wrap(IntStream.range(0, delta.length()).parallel().mapToObj(dataIndex -> {
                        @Nullable final Tensor deltaTensor = delta.get(dataIndex);
                        @Nonnull final Tensor passbackTensor = new Tensor(inputDataDimensions);
                        ImgTileAssemblyLayer.copy(deltaTensor, passbackTensor, -_positionX, -_totalHeight);
                        deltaTensor.freeRef();
                        return passbackTensor;
                    }).toArray(i -> new Tensor[i]));
                    in.accumulate(buffer, tensorArray);
                }
                positionX += inputDataDimensions[0];
                inputIndex += 1;
            }
            totalHeight += rowHeight;
        }
    }) {

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

        @Override
        public boolean isAlive() {
            return inObj[0].isAlive() || !isFrozen();
        }
    };
}

Example 28 with Result

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

the class ImgTileSubnetLayer method evalAndFree.

@Nullable
@Override
public Result evalAndFree(@Nonnull final Result... inObj) {
    assert 1 == inObj.length;
    Result input = inObj[0];
    @Nonnull final int[] inputDims = input.getData().getDimensions();
    assert 3 == inputDims.length;
    int cols = (int) (Math.ceil((inputDims[0] - width) * 1.0 / strideX) + 1);
    int rows = (int) (Math.ceil((inputDims[1] - height) * 1.0 / strideY) + 1);
    if (cols == 1 && rows == 1)
        return getInner().eval(inObj);
    Result[] results = new Result[rows * cols];
    TensorList[] passback = new TensorList[rows * cols];
    int index = 0;
    AtomicInteger passbacks = new AtomicInteger(0);
    for (int row = 0; row < rows; row++) {
        for (int col = 0; col < cols; col++) {
            int positionX = col * strideX;
            int positionY = row * strideY;
            assert positionX >= 0;
            assert positionY >= 0;
            assert positionX < inputDims[0];
            assert positionY < inputDims[1];
            final int finalIndex = index;
            Result selectedTile = new ImgTileSelectLayer(width, height, positionX, positionY).eval(new Result(input.getData(), (ctx, delta) -> {
                passback[finalIndex] = delta;
                if (passbacks.incrementAndGet() == rows * cols) {
                    passbacks.set(0);
                    TensorList reassembled = new ImgTileAssemblyLayer(cols, rows).evalAndFree(Arrays.stream(passback).map(t -> new Result(t, (c2, d2) -> {
                    })).toArray(i -> new Result[i])).getDataAndFree();
                    inObj[0].accumulate(ctx, reassembled);
                }
            }) {

                @Override
                protected void _free() {
                    inObj[0].freeRef();
                    super._free();
                }
            });
            results[index] = getInner().eval(selectedTile);
            index = index + 1;
        }
    }
    inObj[0].getData().freeRef();
    return new ImgTileAssemblyLayer(cols, rows).eval(results);
}

Example 29 with Result

use of com.simiacryptus.mindseye.lang.Result 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 30 with Result

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

the class DAGNetwork method buildExeCtx.

/**
 * Build handler ctx graph evaluation context.
 *
 * @param inputs the inputs
 * @return the graph evaluation context
 */
@Nonnull
public GraphEvaluationContext buildExeCtx(@Nonnull final Result... inputs) {
    assert inputs.length == inputHandles.size() : inputs.length + " != " + inputHandles.size();
    @Nonnull final GraphEvaluationContext context = new GraphEvaluationContext();
    for (int i = 0; i < inputs.length; i++) {
        UUID key = inputHandles.get(i);
        Result input = inputs[i];
        if (!context.calculated.containsKey(key)) {
            input.getData().addRef();
            context.calculated.put(key, new Singleton<CountingResult>().set(new CountingResult(input)));
        }
    }
    context.expectedCounts.putAll(getNodes().stream().flatMap(t -> {
        return Arrays.stream(t.getInputs()).map(n -> n.getId());
    }).filter(x -> !inputHandles.contains(x)).collect(Collectors.groupingBy(x -> x, Collectors.counting())));
    return context;
}