[incubator-tvm] branch master updated: [Tutorial][Quantization] Fix incorrect name of calibration mode (#5150)

[wu...@apache.org]

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

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


The following commit(s) were added to refs/heads/master by this push:
     new a1d6fc9  [Tutorial][Quantization] Fix incorrect name of calibration mode (#5150)
a1d6fc9 is described below

commit a1d6fc95042c9df9dd07fe537a40f3bedc62ef72
Author: Wuwei Lin <vi...@gmail.com>
AuthorDate: Wed Mar 25 18:27:17 2020 -0400

    [Tutorial][Quantization] Fix incorrect name of calibration mode (#5150)
---
 tutorials/frontend/deploy_quantized.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tutorials/frontend/deploy_quantized.py b/tutorials/frontend/deploy_quantized.py
index 5af9fc9..2586318 100644
--- a/tutorials/frontend/deploy_quantized.py
+++ b/tutorials/frontend/deploy_quantized.py
@@ -132,7 +132,7 @@ def quantize(mod, params, data_aware):
         with relay.quantize.qconfig(calibrate_mode='kl_divergence', weight_scale='max'):
             mod = relay.quantize.quantize(mod, params, dataset=calibrate_dataset())
     else:
-        with relay.quantize.qconfig(calibrate_mode='global', global_scale=8.0):
+        with relay.quantize.qconfig(calibrate_mode='global_scale', global_scale=8.0):
             mod = relay.quantize.quantize(mod, params)
     return mod