From 546b44844156a9a5cfe4aa52ef1a0feacc139584 Mon Sep 17 00:00:00 2001
From: yeyunpeng2020 <yeyunpeng1@huawei.com>
Date: Thu, 16 Dec 2021 17:13:45 +0800
Subject: [PATCH] post training delete unused quantization op

---
 .../lite/test/config/models_posttraining.cfg  | 20 ++++++++---------
 .../quantizer/full_quant_quantizer.cc         | 22 +++++--------------
 2 files changed, 15 insertions(+), 27 deletions(-)

diff --git a/mindspore/lite/test/config/models_posttraining.cfg b/mindspore/lite/test/config/models_posttraining.cfg
index 8342e31abd9..adb1c860a7d 100644
--- a/mindspore/lite/test/config/models_posttraining.cfg
+++ b/mindspore/lite/test/config/models_posttraining.cfg
@@ -1,10 +1,10 @@
-ml_face_mnet 64.6 816040
-ml_face_landmark_2 0.6 466408
-mobilenet.tflite 0.4 25592
-transformer_20200831_encoder_fp32.tflite;36 73.5 54250848
-transformer_20200831_decoder_fp32.tflite;11 15.8 12947024
-ml_face_mnet_image 54.1 816048
-resnet.tflite 0.4 63864
-0916_ct_ddd_culane_dlav0_withSigmoid_noMerge.onnx 48 21963056
-v3plus512_512_op11.onnx 47 6026648
-resnet_image.mindir 9.8 38580896
+ml_face_mnet 58.2 827064
+ml_face_landmark_2 0.8 472136
+mobilenet.tflite 0.4 26040
+transformer_20200831_encoder_fp32.tflite;36 13.4 54319144
+transformer_20200831_decoder_fp32.tflite;11 10.0 12970744
+ml_face_mnet_image 47.9 827072
+resnet.tflite 0.4 69272
+0916_ct_ddd_culane_dlav0_withSigmoid_noMerge.onnx 46.6 22077872
+v3plus512_512_op11.onnx 43.1 6027648
+resnet_image.mindir 7.0 38911216
diff --git a/mindspore/lite/tools/converter/quantizer/full_quant_quantizer.cc b/mindspore/lite/tools/converter/quantizer/full_quant_quantizer.cc
index 0fb5306746b..9e246e5c2a9 100644
--- a/mindspore/lite/tools/converter/quantizer/full_quant_quantizer.cc
+++ b/mindspore/lite/tools/converter/quantizer/full_quant_quantizer.cc
@@ -538,10 +538,6 @@ void FullQuantQuantizer::InitCpuConfig() {
     prim::kPrimConv2DFusion,
     prim::kPrimFullConnection,
     prim::kPrimMatMul,
-    prim::kPrimMaxPoolFusion,
-    prim::kPrimAvgPoolFusion,
-    prim::kPrimLayerNormFusion,
-    // prim::kPrimConv2dTransposeFusion, // Precision needs to be optimized.
     // Memory
     prim::kPrimReshape,
     prim::kPrimTranspose,
@@ -554,14 +550,6 @@ void FullQuantQuantizer::InitCpuConfig() {
     prim::kPrimGather,
     prim::kPrimReduceFusion,
     prim::kPrimAffine,
-    // Arithmetic
-    prim::kPrimAddFusion,
-    prim::kPrimActivation,
-    prim::kPrimMulFusion,
-    prim::kPrimDivFusion,
-    prim::kPrimSqrt,
-    prim::kPrimPowFusion,
-    prim::kPrimEltwise,
   };
   skip_check_dtype_ops_ = {prim::kPrimTupleGetItem, prim::kPrimShape};
   per_channel_ops_ = {prim::kPrimConv2DFusion, prim::kPrimConv2dTransposeFusion, prim::kPrimMatMul,
@@ -587,19 +575,19 @@ void FullQuantQuantizer::InitKirinConfig() {
 void FullQuantQuantizer::InitQMinMax() {
   MS_ASSERT(activation_quant_data_type_ == kNumberTypeInt8 || activation_quant_data_type_ == kNumberTypeUInt8);
   if (activation_quant_data_type_ == kNumberTypeInt8) {
-    activation_q_min_ = QuantMin(this->bit_num_, false, true);  // -127
-    activation_q_max_ = QuantMax(this->bit_num_, false);        // 127
+    activation_q_min_ = QuantMin(this->bit_num_, false, activation_symmetry_);  // -128
+    activation_q_max_ = QuantMax(this->bit_num_, false);                        // 127
   } else if (activation_quant_data_type_ == kNumberTypeUInt8) {
     activation_q_min_ = QuantMin(this->bit_num_, true, false);  // 0
     activation_q_max_ = QuantMax(this->bit_num_, true);         // 255
   }
   MS_ASSERT(weight_data_type_ == kNumberTypeInt8 || weight_data_type_ == kNumberTypeUInt8);
   if (weight_data_type_ == kNumberTypeInt8) {
-    weight_q_max_ = QuantMax(this->bit_num_, false);        // 127
-    weight_q_min_ = QuantMin(this->bit_num_, false, true);  // -127
+    weight_q_min_ = QuantMin(this->bit_num_, false, weight_symmetry_);  // -127
+    weight_q_max_ = QuantMax(this->bit_num_, false);                    // 127
   } else if (activation_quant_data_type_ == kNumberTypeUInt8) {
-    weight_q_max_ = QuantMax(this->bit_num_, true);         // 255
     weight_q_min_ = QuantMin(this->bit_num_, true, false);  // 0
+    weight_q_max_ = QuantMax(this->bit_num_, true);         // 255
   }
 }