ZhennanQin commented on a change in pull request #12530: Implement mkldnn
convolution fusion and quantization.
URL: https://github.com/apache/incubator-mxnet/pull/12530#discussion_r220032426
##########
File path: include/mxnet/c_api.h
##########
@@ -1535,6 +1534,15 @@ MXNET_DLL int
MXSetCalibTableToQuantizedSymbol(SymbolHandle qsym_handle,
const float* high_quantiles,
SymbolHandle* ret_sym_handle);
+/*!
+ * \brief Run subgraph pass based on the backend provided
+ * \param sym_handle symbol to be converted
+ * \param backend backend names for subgraph pass
+ * \param ret_sym_handle returned symbol
+ */
+MXNET_DLL int MXGenBackendSubgraph(SymbolHandle sym_handle, const char
*backend,
+ SymbolHandle *ret_sym_handle);
+
Review comment:
It's not for testing, but for quantization script. For mkldnn quantization,
we agreed to do fusion first, and then do quantization. So on python side, we
need an api to generate fused graph, and then pass it to quantization pass.
Otherwise, we have to allow simple_bind returning the graph after subgraph pass.
----------------------------------------------------------------
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
