!9642 add gpu benchmark scripts for pynative mode

From: @chujinjin
Reviewed-by: @jjfeing,@limingqi107
Signed-off-by: @limingqi107

model_zoo/official/cv/nasnet/src/nasnet_a_mobile.py

@@ -813,6 +813,7 @@ class NASNetAMobile(nn.Cell):
         self.classifier = nn.Dense(in_channels=24*filters, out_channels=num_classes)
         self.shape = P.Shape()
         self.reshape = P.Reshape()
+        self.avg_pool = nn.AvgPool2d(kernel_size=7, stride=1)
         self._initialize_weights()
 
     def _initialize_weights(self):
@@ -867,7 +868,7 @@ class NASNetAMobile(nn.Cell):
         x_cell_15 = self.cell_15(x_cell_14, x_cell_13)
 
         x_cell_15 = self.relu(x_cell_15)
-        x_cell_15 = nn.AvgPool2d(F.shape(x_cell_15)[2:])(x_cell_15)  # global average pool
+        x_cell_15 = self.avg_pool(x_cell_15)  # global average pool
         x_cell_15 = self.reshape(x_cell_15, (self.shape(x_cell_15)[0], -1,))
         x_cell_15 = self.dropout(x_cell_15)
         logits = self.classifier(x_cell_15)

model_zoo/official/cv/resnet/gpu_resnet_benchmark.py

@@ -39,6 +39,7 @@ parser.add_argument('--epoch_size', type=str, default="2", help='Epoch_size: def
 parser.add_argument('--print_per_steps', type=str, default="20", help='Print loss and time per steps: default 20')
 parser.add_argument('--run_distribute', type=ast.literal_eval, default=False, help='Run distribute')
 parser.add_argument('--dataset_path', type=str, default=None, help='Imagenet dataset path')
+parser.add_argument('--mode', type=str, default="GRAPH", choices=["GRAPH", "PYNATIVE"], help='Execute mode')
 parser.add_argument('--dtype', type=str, choices=["fp32", "fp16", "FP16", "FP32"], default="fp16",\
      help='Compute data type fp32 or fp16: default fp16')
 args_opt = parser.parse_args()
@@ -119,7 +120,11 @@ if __name__ == '__main__':
     compute_type = str(args_opt.dtype).lower()
 
     # init context
-    context.set_context(mode=context.GRAPH_MODE, device_target=dev, save_graphs=False)
+    if args_opt.mode == "GRAPH":
+        mode = context.GRAPH_MODE
+    else:
+        mode = context.PYNATIVE_MODE
+    context.set_context(mode=mode, device_target=dev, save_graphs=False)
     if args_opt.run_distribute:
         init()
         context.set_auto_parallel_context(device_num=get_group_size(), parallel_mode=ParallelMode.DATA_PARALLEL,
@@ -174,10 +179,15 @@ if __name__ == '__main__':
         model = Model(net, loss_fn=loss, optimizer=opt, loss_scale_manager=loss_scale, metrics={'acc'},
                       amp_level="O2", keep_batchnorm_fp32=False)
     # define callbacks
+    if mode == context.PYNATIVE_MODE:
+        print_per_steps = 1
     time_cb = MyTimeMonitor(total_batch, print_per_steps)
     loss_cb = LossMonitor()
     cb = [time_cb, loss_cb]
 
     # train model
     print("========START RESNET50 GPU BENCHMARK========")
-    model.train(int(epoch_size * step_size / print_per_steps), dataset, callbacks=cb, sink_size=print_per_steps)
+    if mode == context.GRAPH_MODE:
+        model.train(int(epoch_size * step_size / print_per_steps), dataset, callbacks=cb, sink_size=print_per_steps)
+    else:
+        model.train(epoch_size, dataset, callbacks=cb)