[incubator-mxnet] branch master updated: Add documentation on GPU performance on Quantization example (#13145)

[zh...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

zhasheng pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git


The following commit(s) were added to refs/heads/master by this push:
     new 088ae79  Add documentation on GPU performance on Quantization example (#13145)
088ae79 is described below

commit 088ae79f6b402ab549d1261f8beda0df50d0a2f6
Author: Kalyanee Chendke <k_...@hotmail.com>
AuthorDate: Wed Nov 7 14:44:34 2018 -0800

    Add documentation on GPU performance on Quantization example (#13145)
    
    * Add documentation on GPU performance
    
    * Update README.md
---
 example/quantization/README.md             | 4 +++-
 example/quantization/imagenet_inference.py | 1 +
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/example/quantization/README.md b/example/quantization/README.md
index 7f68dd7..0e63cd8 100644
--- a/example/quantization/README.md
+++ b/example/quantization/README.md
@@ -320,4 +320,6 @@ the console to run model quantization for a specific configuration.
 - `launch_inference.sh` This is a shell script that calculate the accuracies of all the quantized models generated
 by invoking `launch_quantize.sh`.
 
-**NOTE**: This example has only been tested on Linux systems.
\ No newline at end of file
+**NOTE**: 
+- This example has only been tested on Linux systems.
+- Performance is expected to decrease with GPU, however the memory footprint of a quantized model is smaller. The purpose of the quantization implementation is to minimize accuracy loss when converting FP32 models to INT8. MXNet community is working on improving the performance. 
\ No newline at end of file
diff --git a/example/quantization/imagenet_inference.py b/example/quantization/imagenet_inference.py
index 7d380d3..3fdb52f 100644
--- a/example/quantization/imagenet_inference.py
+++ b/example/quantization/imagenet_inference.py
@@ -93,6 +93,7 @@ def score(sym, arg_params, aux_params, data, devs, label_name, max_num_examples,
     if logger is not None:
         logger.info('Finished inference with %d images' % num)
         logger.info('Finished with %f images per second', speed)
+        logger.warn('Note: GPU performance is expected to be slower than CPU. Please refer quantization/README.md for details')
         for m in metrics:
             logger.info(m.get())