ZhennanQin commented on a change in pull request #13697: [MKLDNN] Enable signed
int8 support for convolution.
URL: https://github.com/apache/incubator-mxnet/pull/13697#discussion_r253345880
##########
File path: python/mxnet/contrib/quantization.py
##########
@@ -286,12 +283,12 @@ def _get_optimal_threshold(arr, num_bins=8001,
num_quantized_bins=255):
min_val = np.min(arr)
max_val = np.max(arr)
th = max(abs(min_val), abs(max_val))
+ if min_val >= 0:
+ num_quantized_bins = (num_quantized_bins // 2) * 4 + 1
Review comment:
Your understand is correct. Should change to `num_quantized_bins =
num_quantized_bins * 2 + 1`. But I removed this from this PR as it may affact
GPU accuracy.
----------------------------------------------------------------
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
