Question

我使用tf.saved_model.builder.SavedModelBuilder保存了张量流模型。但是，当我尝试在java中进行预测时，在大多数情况下它返回相同的结果（对于fc8（alexnet）softmax之前的层）在某些情况下，它会产生一些真正不同的结果，它最有可能是正确的，所以我认为培训是正常的。有没有人经历过这个？有没有人知道什么是错的？

我的Java实现：

Tensor image = constructAndExecuteGraphToNormalizeImage(imageBytes);    
Tensor result = s.runner().feed("input_tensor", image).feed("Placeholder_1",t).fetch("fc8/fc8").run().get(0);

private static Tensor constructAndExecuteGraphToNormalizeImage(byte[] imageBytes) {
    try (Graph g = new Graph()) {
        TF.GraphBuilder b = new TF.GraphBuilder(g);
        // Some constants specific to the pre-trained model at:
        // https://storage.googleapis.com/download.tensorflow.org/models/inception5h.zip
        //
        // - The model was trained with images scaled to 224x224 pixels.
        // - The colors, represented as R, G, B in 1-byte each were converted to
        //   float using (value - Mean)/Scale.
        final int H = 227;
        final int W = 227;
        final float mean = 117f;
        final float scale = 1f;

        // Since the graph is being constructed once per execution here, we can use a constant for the
        // input image. If the graph were to be re-used for multiple input images, a placeholder would
        // have been more appropriate.
        final Output input = b.constant("input", imageBytes);
        final Output output =
                b.div(
                        b.sub(
                                b.resizeBilinear(
                                        b.expandDims(
                                                b.cast(b.decodeJpeg(input, 3), DataType.FLOAT),
                                                b.constant("make_batch", 0)),
                                        b.constant("size", new int[] {H, W})),
                                b.constant("mean", mean)),
                        b.constant("scale", scale));
        try (Session s = new Session(g)) {
            return s.runner().fetch(output.op().name()).run().get(0);
        }
    }
}

Answer 1

我假设您的图表中没有任何随机操作，例如丢失。（似乎是这种情况，因为你经常得到相同的结果）。

唉，some operations in tensorflow seem to be non-deterministic，例如减少和卷积。我们必须忍受这样一个事实，即张量流的网络是随机动物：它们的表现可以在统计上接近，但它们的输出是非确定性的。

（我相信其他一些框架，比如Theano在提出确定性操作方面比tensorflow更远。）

每个推断都有相同的预测

1 个答案: