From a13f88c66f5926bc71db588ca84e0240267d33ba Mon Sep 17 00:00:00 2001 From: Andre Moeller Date: Tue, 29 May 2018 15:57:23 -0700 Subject: [PATCH] fix link to npy --- README.rst | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/README.rst b/README.rst index 24654215c0..2789e12f74 100644 --- a/README.rst +++ b/README.rst @@ -1957,12 +1957,10 @@ You can provide your own implementations for these functions in your hosting scr If you omit any definition then the SageMaker Chainer model server will use its default implementation for that function. -The ``RealTimePredictor`` used by Chainer in the SageMaker Python SDK serializes NumPy arrays to the NPY_ format +The ``RealTimePredictor`` used by Chainer in the SageMaker Python SDK serializes NumPy arrays to the `NPY `_ format by default, with Content-Type ``application/x-npy``. The SageMaker Chainer model server can deserialize NPY-formatted data (along with JSON and CSV data). -.. _NPY https://docs.scipy.org/doc/numpy/neps/npy-format.html - If you rely solely on the SageMaker Chainer model server defaults, you get the following functionality: - Prediction on models that implement the ``__call__`` method @@ -1998,7 +1996,7 @@ Where ``request_body`` is a byte buffer and ``request_content_type`` is a Python The SageMaker Chainer model server provides a default implementation of ``input_fn``. This function deserializes JSON, CSV, or NPY encoded data into a NumPy array. -Default NPY deserialization requires ``request_body`` to follow the NPY_ format. For Chainer, the Python SDK +Default NPY deserialization requires ``request_body`` to follow the `NPY `_ format. For Chainer, the Python SDK defaults to sending prediction requests with this format. Default json deserialization requires ``request_body`` contain a single json list.