lihaofd commented on a change in pull request #12922: Support Quantized Fully
Connected by INT8 GEMM
URL: https://github.com/apache/incubator-mxnet/pull/12922#discussion_r229146882
##########
File path: tests/python/quantization/test_quantization.py
##########
@@ -283,16 +283,16 @@ def check_quantized_fc(data_shape, num_hidden, no_bias,
qdtype, flatten=True):
fc_fp32_exe = fc_fp32.simple_bind(ctx=mx.current_context(),
grad_req='null')
if qdtype == 'uint8':
data_low = 0.0
- data_high = 127.0
+ data_high = 63.0
Review comment:
Change data range from (-127,127) to (-63, 63) to avoid overflow when using
igemm sometimes
----------------------------------------------------------------
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:
us...@infra.apache.org
With regards,
Apache Git Services
