npu optimization and add models

mindspore/lite/src/delegate/npu/pass/npu_insert_transform_pass.cc

@@ -60,6 +60,8 @@ int NPUInsertTransformPass::GetInsertState(NPUOp *op) {
     inputs.size() + std::max(std::max(op->out_ops().size(), static_cast<size_t>(1)), op->outputs().size());
   size_t transpose_input_num = 0;
   size_t transpose_output_num = 0;
+  size_t graph_input_num = 0;
+  size_t graph_output_num = 0;
   bool need_pre_insert = false;
   bool need_post_insert = false;
   // count number of input tensor from nc2nh and output tensor to nh2nc
@@ -70,10 +72,16 @@ int NPUInsertTransformPass::GetInsertState(NPUOp *op) {
     } else {
       need_pre_insert = true;
     }
+    if (in_op == nullptr) {
+      graph_input_num++;
+    }
   }
   if (op->out_ops().empty()) {
     need_post_insert = true;
   }
+  if (op->outputs().size() > op->out_ops().size()) {
+    graph_output_num = op->outputs().size() - op->out_ops().size();
+  }
   for (const auto out_op : op->out_ops()) {
     if (NPUPassUtils::IsNhwc2Nchw(out_op)) {
       transpose_output_num++;
@@ -82,10 +90,12 @@ int NPUInsertTransformPass::GetInsertState(NPUOp *op) {
     }
   }
 
-  // won't insert any thing if num of transpose tensor is smaller than half of total input output.
+  // won't insert any thing if num of transpose tensor is smaller than half of total op inputs and op outputs, unless
+  // current op is the graph input or output op, since we should avoid to build a single op subgraph in this case.
   // won't insert if total input output are all transpose tensor, the fusion pass will handle this.
   size_t transpose_tensor_num = transpose_input_num + transpose_output_num;
-  if (transpose_tensor_num == 0 || transpose_tensor_num * 2 < in_out_tensor_num ||
+  size_t connected_in_out_tensor_num = in_out_tensor_num - graph_output_num - graph_input_num;
+  if (transpose_tensor_num == 0 || transpose_tensor_num * 2 < connected_in_out_tensor_num ||
       transpose_tensor_num == in_out_tensor_num) {
     return InsertNone;
   }

mindspore/lite/test/config/models_npu.cfg

@@ -89,3 +89,4 @@ ml_video_edit_makeup_mobilenetv203.onnx 2
 ml_video_edit_hairline_segmentation;3 0.5
 ml_video_edit_hair_dyeing_migrate_v2.onnx;4:3,4,1,2 0.5
 Modify_Out_ml_audio_kit_encoder_v5.pb;6:5,2,1,4,6,3;1:1,32:1,32:1,32:1:1,32
+ml_video_edit_hair_dyeing_migrate_v2_fix.onnx;4 1.5

mindspore/lite/test/config/models_onnx.cfg

@@ -103,4 +103,5 @@ tiny-yolov3-11.onnx;2;1,224,224,3:1,2 3
 # cur acc for ml_video_edit_art_transfer is 2+%
 ml_video_edit_art_transfer.onnx;3
 ssd-10.onnx;;;;calib_only
-Q888_CV_face_recognition_self.onnx
+Q888_CV_face_recognition_self.onnx
+ml_video_edit_hair_dyeing_migrate_v2_fix.onnx;4

mindspore/lite/test/config/models_onnx_fp16.cfg

@@ -103,3 +103,4 @@ ml_video_edit_makeup_mobilenetv203.onnx 4
 # The input of ml_video_edit_hair_dyeing_migrate_v2.onnx should be between [0, 1]
 ml_video_edit_hair_dyeing_migrate_v2.onnx;4:3,4,1,2 2.5
 Q888_CV_face_recognition_self.onnx 3.5
+ml_video_edit_hair_dyeing_migrate_v2_fix.onnx;4 3

mindspore/lite/test/config/models_tflite.cfg

@@ -200,3 +200,4 @@ lite-model_albert_lite_base_squadv1_metadata_1.tflite;3:2,3,1
 lite-model_mobilebert_1_metadata_1.tflite;3
 Modify_Out_hiai_vad.tflite;2
 add_uint8.tflite;2
+coco_ssd_mobilenet_v1_1.0.tflite

mindspore/lite/test/config/models_tflite_fp16.cfg

@@ -220,3 +220,4 @@ hdc_tb_cn_neg.tflite;3:3,1,2 295
 hiai_cv_labelDetectorModel_v3.tflite;2:2,1 2
 ml_headpose_pb2tflite.tflite;3:2,3,1;1,64,64,3:16:16 1
 ml_ei_headpose_pb2tflite.tflite;3:2,3,1;1,64,64,3:16:16 0.6
+coco_ssd_mobilenet_v1_1.0.tflite

mindspore/lite/test/st/scripts/run_benchmark_codegen.sh

@@ -267,29 +267,25 @@ fi
 if [[ $backend == "all" || $backend == "codegen" || $backend == "x86_codegen" || $backend == "x86_codegen_parallel" || $backend == "codegen&train" ]]; then
     # Run on x86-codegen-parallel
     echo "start Run x86 codegen parallel ..."
-    Run_x86_codegen ${build_parallal_path} ${ms_models_path} ${models_codegen_parallel_config} ${run_x86_codegen_parallel_log_file} ${run_benchmark_result_file} &
-    Run_x86_codegen_parallel_PID=$!
-    sleep 1
+    Run_x86_codegen ${build_parallal_path} ${ms_models_path} ${models_codegen_parallel_config} ${run_x86_codegen_parallel_log_file} ${run_benchmark_result_file}
+    Run_x86_codegen_parallel_status=$?
 fi
 if [[ $backend == "all" || $backend == "codegen" || $backend == "arm64_codegen" || $backend == "codegen&train" ]]; then
     # Run on codegen
     echo "start Run arm64 codegen ..."
     Run_arm_codegen ${build_path} ${ms_models_path} ${models_codegen_config} ${run_arm64_fp32_codegen_log_file} ${run_benchmark_result_file} ${device_id} "arm64"
     Run_arm64_codegen_status=$?
-    sleep 1
 fi
 if [[ $backend == "all" || $backend == "codegen" || $backend == "arm32_codegen" || $backend == "codegen&train" ]]; then
     # Run on arm32 codegen
     echo "start Run arm32 codegen ..."
     Run_arm_codegen ${build_path} ${ms_models_path} ${models_codegen_config} ${run_arm32_fp32_codegen_log_file} ${run_benchmark_result_file} ${device_id} "arm32"
     Run_arm32_codegen_status=$?
-    sleep 1
 fi
 
 if [[ $backend == "all" || $backend == "codegen" || $backend == "x86_codegen" || $backend == "codegen&train" ]]; then
     wait ${Run_x86_codegen_PID}
     Run_x86_codegen_status=$?
-
     if [[ ${Run_x86_codegen_status} != 0 ]];then
         echo "Run_x86 codegen failed"
         cat ${run_x86_codegen_log_file}
@@ -297,9 +293,6 @@ if [[ $backend == "all" || $backend == "codegen" || $backend == "x86_codegen" ||
     fi
 fi
 if [[ $backend == "all" || $backend == "codegen" || $backend == "x86_codegen" || $backend == "x86_codegen_parallel" || $backend == "codegen&train" ]]; then
-    wait ${Run_x86_codegen_parallel_PID}
-    Run_x86_codegen_parallel_status=$?
-
     if [[ ${Run_x86_codegen_parallel_status} != 0 ]];then
         echo "Run_x86 codegen parallel failed"
         cat ${run_x86_codegen_log_file}