You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by ma...@apache.org on 2018/08/03 11:02:23 UTC
[incubator-mxnet] branch master updated: Disable flaky mkldnn
test_requantize_int32_to_int8 (#11748)
This is an automated email from the ASF dual-hosted git repository.
marcoabreu 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 32c2e15 Disable flaky mkldnn test_requantize_int32_to_int8 (#11748)
32c2e15 is described below
commit 32c2e159ae63458b9aa0231761c8fec38be42df4
Author: Kellen Sunderland <ke...@gmail.com>
AuthorDate: Fri Aug 3 13:02:15 2018 +0200
Disable flaky mkldnn test_requantize_int32_to_int8 (#11748)
---
tests/python/quantization/test_quantization.py | 1 +
1 file changed, 1 insertion(+)
diff --git a/tests/python/quantization/test_quantization.py b/tests/python/quantization/test_quantization.py
index 359bbee..08303c8 100644
--- a/tests/python/quantization/test_quantization.py
+++ b/tests/python/quantization/test_quantization.py
@@ -77,6 +77,7 @@ def test_dequantize_int8_to_float32():
@with_seed()
+@unittest.skip('Flaky test, tracked in: https://github.com/apache/incubator-mxnet/issues/11747')
def test_requantize_int32_to_int8():
def quantized_int32_to_float(qdata, min_range, max_range):
assert qdata.dtype == 'int32'