szha closed pull request #13145: Add documentation on GPU performance on
Quantization example
URL: https://github.com/apache/incubator-mxnet/pull/13145
This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:
As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):
diff --git a/example/quantization/README.md b/example/quantization/README.md
index 7f68dd79540..0e63cd84ede 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 7d380d3e1b4..3fdb52f40cb 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())
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
