COMPMID-1367: Enable NHWC in graph examples

Change-Id: Iabc54a3a1bdcd46a9a921cda39c7c85fef672b72
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/141449
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>

1 files changed, 84 insertions, 79 deletions

diff --git a/examples/graph_inception_v4.cpp b/examples/graph_inception_v4.cpp
index 4e405923fc..b61acfcb3f 100644
--- a/examples/graph_inception_v4.cpp
+++ b/examples/graph_inception_v4.cpp
@@ -60,7 +60,6 @@ public:
 
         // Checks
         ARM_COMPUTE_EXIT_ON_MSG(arm_compute::is_data_type_quantized_asymmetric(common_params.data_type), "Unsupported data type!");
-        ARM_COMPUTE_EXIT_ON_MSG(common_params.data_layout == DataLayout::NHWC, "Unsupported data layout!");
 
         // Print parameter values
         std::cout << common_params << std::endl;
@@ -71,13 +70,19 @@ public:
         // Create a preprocessor object
         std::unique_ptr<IPreprocessor> preprocessor = arm_compute::support::cpp14::make_unique<TFPreproccessor>();
 
+        // Create input descriptor
+        const TensorShape tensor_shape     = permute_shape(TensorShape(299U, 299U, 3U, 1U), DataLayout::NCHW, common_params.data_layout);
+        TensorDescriptor  input_descriptor = TensorDescriptor(tensor_shape, common_params.data_type).set_layout(common_params.data_layout);
+
+        // Set weights trained layout
+        const DataLayout weights_layout = DataLayout::NCHW;
+
         graph << common_params.target
               << common_params.fast_math_hint
-              << InputLayer(TensorDescriptor(TensorShape(299U, 299U, 3U, 1U), common_params.data_type),
-                            get_input_accessor(common_params, std::move(preprocessor), false))
+              << InputLayer(input_descriptor, get_input_accessor(common_params, std::move(preprocessor), false))
               // Conv2d_1a_3x3
               << ConvolutionLayer(3U, 3U, 32U,
-                                  get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Conv2d_1a_3x3_weights.npy"),
+                                  get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Conv2d_1a_3x3_weights.npy", weights_layout),
                                   std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(2, 2, 0, 0))
               << BatchNormalizationLayer(get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Conv2d_1a_3x3_BatchNorm_moving_mean.npy"),
                                          get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Conv2d_1a_3x3_BatchNorm_moving_variance.npy"),
@@ -87,7 +92,7 @@ public:
               << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
               // Conv2d_2a_3x3
               << ConvolutionLayer(3U, 3U, 32U,
-                                  get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Conv2d_2a_3x3_weights.npy"),
+                                  get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Conv2d_2a_3x3_weights.npy", weights_layout),
                                   std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
               << BatchNormalizationLayer(get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Conv2d_2a_3x3_BatchNorm_moving_mean.npy"),
                                          get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Conv2d_2a_3x3_BatchNorm_moving_variance.npy"),
@@ -97,7 +102,7 @@ public:
               << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
               // Conv2d_2b_3x3
               << ConvolutionLayer(3U, 3U, 64U,
-                                  get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Conv2d_2b_3x3_weights.npy"),
+                                  get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Conv2d_2b_3x3_weights.npy", weights_layout),
                                   std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 1, 1))
               << BatchNormalizationLayer(get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Conv2d_2b_3x3_BatchNorm_moving_mean.npy"),
                                          get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Conv2d_2b_3x3_BatchNorm_moving_variance.npy"),
@@ -106,35 +111,35 @@ public:
                                          0.001f)
               << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU));
 
-        graph << get_mixed_3a(data_path);
-        graph << get_mixed_4a(data_path);
-        graph << get_mixed_5a(data_path);
+        graph << get_mixed_3a(data_path, weights_layout);
+        graph << get_mixed_4a(data_path, weights_layout);
+        graph << get_mixed_5a(data_path, weights_layout);
         // 4 inception A blocks
-        graph << get_inceptionA_block(data_path, "Mixed_5b");
-        graph << get_inceptionA_block(data_path, "Mixed_5c");
-        graph << get_inceptionA_block(data_path, "Mixed_5d");
-        graph << get_inceptionA_block(data_path, "Mixed_5e");
+        graph << get_inceptionA_block(data_path, weights_layout, "Mixed_5b");
+        graph << get_inceptionA_block(data_path, weights_layout, "Mixed_5c");
+        graph << get_inceptionA_block(data_path, weights_layout, "Mixed_5d");
+        graph << get_inceptionA_block(data_path, weights_layout, "Mixed_5e");
         // reduction A block
-        graph << get_reductionA_block(data_path);
+        graph << get_reductionA_block(data_path, weights_layout);
         // 7 inception B blocks
-        graph << get_inceptionB_block(data_path, "Mixed_6b");
-        graph << get_inceptionB_block(data_path, "Mixed_6c");
-        graph << get_inceptionB_block(data_path, "Mixed_6d");
-        graph << get_inceptionB_block(data_path, "Mixed_6e");
-        graph << get_inceptionB_block(data_path, "Mixed_6f");
-        graph << get_inceptionB_block(data_path, "Mixed_6g");
-        graph << get_inceptionB_block(data_path, "Mixed_6h");
+        graph << get_inceptionB_block(data_path, weights_layout, "Mixed_6b");
+        graph << get_inceptionB_block(data_path, weights_layout, "Mixed_6c");
+        graph << get_inceptionB_block(data_path, weights_layout, "Mixed_6d");
+        graph << get_inceptionB_block(data_path, weights_layout, "Mixed_6e");
+        graph << get_inceptionB_block(data_path, weights_layout, "Mixed_6f");
+        graph << get_inceptionB_block(data_path, weights_layout, "Mixed_6g");
+        graph << get_inceptionB_block(data_path, weights_layout, "Mixed_6h");
         // reduction B block
-        graph << get_reductionB_block(data_path);
+        graph << get_reductionB_block(data_path, weights_layout);
         // 3 inception C blocks
-        graph << get_inceptionC_block(data_path, "Mixed_7b");
-        graph << get_inceptionC_block(data_path, "Mixed_7c");
-        graph << get_inceptionC_block(data_path, "Mixed_7d");
+        graph << get_inceptionC_block(data_path, weights_layout, "Mixed_7b");
+        graph << get_inceptionC_block(data_path, weights_layout, "Mixed_7c");
+        graph << get_inceptionC_block(data_path, weights_layout, "Mixed_7d");
         graph << PoolingLayer(PoolingLayerInfo(PoolingType::AVG))
               << FlattenLayer()
               << FullyConnectedLayer(
                   1001U,
-                  get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Logits_Logits_weights.npy"),
+                  get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Logits_Logits_weights.npy", weights_layout),
                   get_weights_accessor(data_path, "/cnn_data/inceptionv4_model/Logits_Logits_biases.npy"))
               << SoftmaxLayer()
               << OutputLayer(get_output_accessor(common_params, 5));
@@ -162,7 +167,7 @@ private:
     Stream             graph;
 
 private:
-    BranchLayer get_mixed_3a(const std::string &data_path)
+    BranchLayer get_mixed_3a(const std::string &data_path, DataLayout weights_layout)
     {
         std::string total_path = "/cnn_data/inceptionv4_model/Mixed_3a_";
 
@@ -171,7 +176,7 @@ private:
 
         SubStream i_b(graph);
         i_b << ConvolutionLayer(3U, 3U, 96U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_3x3_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_3x3_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(2, 2, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_3x3_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_3x3_BatchNorm_moving_variance.npy"),
@@ -183,13 +188,13 @@ private:
         return BranchLayer(BranchMergeMethod::DEPTH_CONCATENATE, std::move(i_a), std::move(i_b));
     }
 
-    BranchLayer get_mixed_4a(const std::string &data_path)
+    BranchLayer get_mixed_4a(const std::string &data_path, DataLayout weights_layout)
     {
         std::string total_path = "/cnn_data/inceptionv4_model/Mixed_4a_";
 
         SubStream i_a(graph);
         i_a << ConvolutionLayer(1U, 1U, 64U,
-                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_BatchNorm_moving_variance.npy"),
@@ -198,7 +203,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(3U, 3U, 96U,
-                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_BatchNorm_moving_variance.npy"),
@@ -209,7 +214,7 @@ private:
 
         SubStream i_b(graph);
         i_b << ConvolutionLayer(1U, 1U, 64U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_BatchNorm_moving_variance.npy"),
@@ -218,7 +223,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(7U, 1U, 64U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_1x7_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_1x7_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 3, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_1x7_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_1x7_BatchNorm_moving_variance.npy"),
@@ -227,7 +232,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(1U, 7U, 64U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0c_7x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0c_7x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 3))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0c_7x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0c_7x1_BatchNorm_moving_variance.npy"),
@@ -236,7 +241,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(3U, 3U, 96U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_1a_3x3_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_1a_3x3_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_1a_3x3_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_1a_3x3_BatchNorm_moving_variance.npy"),
@@ -248,13 +253,13 @@ private:
         return BranchLayer(BranchMergeMethod::DEPTH_CONCATENATE, std::move(i_a), std::move(i_b));
     }
 
-    BranchLayer get_mixed_5a(const std::string &data_path)
+    BranchLayer get_mixed_5a(const std::string &data_path, DataLayout weights_layout)
     {
         std::string total_path = "/cnn_data/inceptionv4_model/Mixed_5a_";
 
         SubStream i_a(graph);
         i_a << ConvolutionLayer(3U, 3U, 192U,
-                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(2, 2, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_BatchNorm_moving_variance.npy"),
@@ -269,13 +274,13 @@ private:
         return BranchLayer(BranchMergeMethod::DEPTH_CONCATENATE, std::move(i_a), std::move(i_b));
     }
 
-    BranchLayer get_inceptionA_block(const std::string &data_path, std::string &&param_path)
+    BranchLayer get_inceptionA_block(const std::string &data_path, DataLayout weights_layout, std::string &&param_path)
     {
         std::string total_path = "/cnn_data/inceptionv4_model/" + param_path + "_";
 
         SubStream i_a(graph);
         i_a << ConvolutionLayer(1U, 1U, 96U,
-                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_BatchNorm_moving_variance.npy"),
@@ -286,7 +291,7 @@ private:
 
         SubStream i_b(graph);
         i_b << ConvolutionLayer(1U, 1U, 64U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_BatchNorm_moving_variance.npy"),
@@ -295,7 +300,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(3U, 3U, 96U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_3x3_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_3x3_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 1, 1))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_3x3_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_3x3_BatchNorm_moving_variance.npy"),
@@ -306,7 +311,7 @@ private:
 
         SubStream i_c(graph);
         i_c << ConvolutionLayer(1U, 1U, 64U,
-                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0a_1x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0a_1x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0a_1x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0a_1x1_BatchNorm_moving_variance.npy"),
@@ -315,7 +320,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(3U, 3U, 96U,
-                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0b_3x3_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0b_3x3_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 1, 1))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0b_3x3_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0b_3x3_BatchNorm_moving_variance.npy"),
@@ -324,7 +329,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(3U, 3U, 96U,
-                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0c_3x3_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0c_3x3_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 1, 1))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0c_3x3_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0c_3x3_BatchNorm_moving_variance.npy"),
@@ -336,7 +341,7 @@ private:
         SubStream i_d(graph);
         i_d << PoolingLayer(PoolingLayerInfo(PoolingType::AVG, 3, PadStrideInfo(1, 1, 1, 1, DimensionRoundingType::CEIL), true))
             << ConvolutionLayer(1U, 1U, 96U,
-                                get_weights_accessor(data_path, total_path + "Branch_3_Conv2d_0b_1x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_3_Conv2d_0b_1x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_3_Conv2d_0b_1x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_3_Conv2d_0b_1x1_BatchNorm_moving_variance.npy"),
@@ -348,13 +353,13 @@ private:
         return BranchLayer(BranchMergeMethod::DEPTH_CONCATENATE, std::move(i_a), std::move(i_b), std::move(i_c), std::move(i_d));
     }
 
-    BranchLayer get_reductionA_block(const std::string &data_path)
+    BranchLayer get_reductionA_block(const std::string &data_path, DataLayout weights_layout)
     {
         std::string total_path = "/cnn_data/inceptionv4_model/Mixed_6a_";
 
         SubStream i_a(graph);
         i_a << ConvolutionLayer(3U, 3U, 384U,
-                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(2, 2, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_BatchNorm_moving_variance.npy"),
@@ -365,7 +370,7 @@ private:
 
         SubStream i_b(graph);
         i_b << ConvolutionLayer(1U, 1U, 192U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_BatchNorm_moving_variance.npy"),
@@ -374,7 +379,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(3U, 3U, 224U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_3x3_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_3x3_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 1, 1))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_3x3_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_3x3_BatchNorm_moving_variance.npy"),
@@ -383,7 +388,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(3U, 3U, 256U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_1a_3x3_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_1a_3x3_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(2, 2, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_1a_3x3_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_1a_3x3_BatchNorm_moving_variance.npy"),
@@ -398,13 +403,13 @@ private:
         return BranchLayer(BranchMergeMethod::DEPTH_CONCATENATE, std::move(i_a), std::move(i_b), std::move(i_c));
     }
 
-    BranchLayer get_inceptionB_block(const std::string &data_path, std::string &&param_path)
+    BranchLayer get_inceptionB_block(const std::string &data_path, DataLayout weights_layout, std::string &&param_path)
     {
         std::string total_path = "/cnn_data/inceptionv4_model/" + param_path + "_";
 
         SubStream i_a(graph);
         i_a << ConvolutionLayer(1U, 1U, 384U,
-                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_BatchNorm_moving_variance.npy"),
@@ -415,7 +420,7 @@ private:
 
         SubStream i_b(graph);
         i_b << ConvolutionLayer(1U, 1U, 192U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_BatchNorm_moving_variance.npy"),
@@ -424,7 +429,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(7U, 1U, 224U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_1x7_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_1x7_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 3, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_1x7_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_1x7_BatchNorm_moving_variance.npy"),
@@ -433,7 +438,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(1U, 7U, 256U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0c_7x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0c_7x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 3))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0c_7x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0c_7x1_BatchNorm_moving_variance.npy"),
@@ -444,7 +449,7 @@ private:
 
         SubStream i_c(graph);
         i_c << ConvolutionLayer(1U, 1U, 192U,
-                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0a_1x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0a_1x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0a_1x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0a_1x1_BatchNorm_moving_variance.npy"),
@@ -453,7 +458,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(1U, 7U, 192U,
-                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0b_7x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0b_7x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 3))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0b_7x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0b_7x1_BatchNorm_moving_variance.npy"),
@@ -462,7 +467,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(7U, 1U, 224U,
-                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0c_1x7_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0c_1x7_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 3, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0c_1x7_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0c_1x7_BatchNorm_moving_variance.npy"),
@@ -471,7 +476,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(1U, 7U, 224U,
-                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0d_7x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0d_7x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 3))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0d_7x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0d_7x1_BatchNorm_moving_variance.npy"),
@@ -480,7 +485,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(7U, 1U, 256U,
-                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0e_1x7_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0e_1x7_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 3, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0e_1x7_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0e_1x7_BatchNorm_moving_variance.npy"),
@@ -492,7 +497,7 @@ private:
         SubStream i_d(graph);
         i_d << PoolingLayer(PoolingLayerInfo(PoolingType::AVG, 3, PadStrideInfo(1, 1, 1, 1, DimensionRoundingType::CEIL), true))
             << ConvolutionLayer(1U, 1U, 128U,
-                                get_weights_accessor(data_path, total_path + "Branch_3_Conv2d_0b_1x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_3_Conv2d_0b_1x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_3_Conv2d_0b_1x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_3_Conv2d_0b_1x1_BatchNorm_moving_variance.npy"),
@@ -504,13 +509,13 @@ private:
         return BranchLayer(BranchMergeMethod::DEPTH_CONCATENATE, std::move(i_a), std::move(i_b), std::move(i_c), std::move(i_d));
     }
 
-    BranchLayer get_reductionB_block(const std::string &data_path)
+    BranchLayer get_reductionB_block(const std::string &data_path, DataLayout weights_layout)
     {
         std::string total_path = "/cnn_data/inceptionv4_model/Mixed_7a_";
 
         SubStream i_a(graph);
         i_a << ConvolutionLayer(1U, 1U, 192U,
-                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_BatchNorm_moving_variance.npy"),
@@ -519,7 +524,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(3U, 3U, 192U,
-                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(2, 2, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_1a_3x3_BatchNorm_moving_variance.npy"),
@@ -530,7 +535,7 @@ private:
 
         SubStream i_b(graph);
         i_b << ConvolutionLayer(1U, 1U, 256U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_BatchNorm_moving_variance.npy"),
@@ -539,7 +544,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(7U, 1U, 256U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_1x7_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_1x7_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 3, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_1x7_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_1x7_BatchNorm_moving_variance.npy"),
@@ -548,7 +553,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(1U, 7U, 320U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0c_7x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0c_7x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 3))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0c_7x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0c_7x1_BatchNorm_moving_variance.npy"),
@@ -557,7 +562,7 @@ private:
                                        0.001f)
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(3U, 3U, 320U,
-                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_1a_3x3_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_1a_3x3_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(2, 2, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_1a_3x3_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_1a_3x3_BatchNorm_moving_variance.npy"),
@@ -572,13 +577,13 @@ private:
         return BranchLayer(BranchMergeMethod::DEPTH_CONCATENATE, std::move(i_a), std::move(i_b), std::move(i_c));
     }
 
-    BranchLayer get_inceptionC_block(const std::string &data_path, std::string &&param_path)
+    BranchLayer get_inceptionC_block(const std::string &data_path, DataLayout weights_layout, std::string &&param_path)
     {
         std::string total_path = "/cnn_data/inceptionv4_model/" + param_path + "_";
 
         SubStream i_a(graph);
         i_a << ConvolutionLayer(1U, 1U, 256U,
-                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_0_Conv2d_0a_1x1_BatchNorm_moving_variance.npy"),
@@ -590,7 +595,7 @@ private:
         SubStream i_b(graph);
         i_b << ConvolutionLayer(
                 1U, 1U, 384U,
-                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_weights.npy"),
+                get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0a_1x1_weights.npy", weights_layout),
                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr),
                 PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(
@@ -604,7 +609,7 @@ private:
         SubStream i_b1(i_b);
         i_b1 << ConvolutionLayer(
                  3U, 1U, 256U,
-                 get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_1x3_weights.npy"),
+                 get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0b_1x3_weights.npy", weights_layout),
                  std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr),
                  PadStrideInfo(1, 1, 1, 0))
              << BatchNormalizationLayer(
@@ -618,7 +623,7 @@ private:
         SubStream i_b2(i_b);
         i_b2 << ConvolutionLayer(
                  1U, 3U, 256U,
-                 get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0c_3x1_weights.npy"),
+                 get_weights_accessor(data_path, total_path + "Branch_1_Conv2d_0c_3x1_weights.npy", weights_layout),
                  std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr),
                  PadStrideInfo(1, 1, 0, 1))
              << BatchNormalizationLayer(
@@ -635,7 +640,7 @@ private:
         SubStream i_c(graph);
         i_c << ConvolutionLayer(
                 1U, 1U, 384U,
-                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0a_1x1_weights.npy"),
+                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0a_1x1_weights.npy", weights_layout),
                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr),
                 PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(
@@ -647,7 +652,7 @@ private:
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(
                 1U, 3U, 448U,
-                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0b_3x1_weights.npy"),
+                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0b_3x1_weights.npy", weights_layout),
                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr),
                 PadStrideInfo(1, 1, 0, 1))
             << BatchNormalizationLayer(
@@ -659,7 +664,7 @@ private:
             << ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
             << ConvolutionLayer(
                 3U, 1U, 512U,
-                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0c_1x3_weights.npy"),
+                get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0c_1x3_weights.npy", weights_layout),
                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr),
                 PadStrideInfo(1, 1, 1, 0))
             << BatchNormalizationLayer(
@@ -673,7 +678,7 @@ private:
         SubStream i_c1(i_c);
         i_c1 << ConvolutionLayer(
                  3U, 1U, 256U,
-                 get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0d_1x3_weights.npy"),
+                 get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0d_1x3_weights.npy", weights_layout),
                  std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr),
                  PadStrideInfo(1, 1, 1, 0))
              << BatchNormalizationLayer(
@@ -687,7 +692,7 @@ private:
         SubStream i_c2(i_c);
         i_c2 << ConvolutionLayer(
                  1U, 3U, 256U,
-                 get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0e_3x1_weights.npy"),
+                 get_weights_accessor(data_path, total_path + "Branch_2_Conv2d_0e_3x1_weights.npy", weights_layout),
                  std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr),
                  PadStrideInfo(1, 1, 0, 1))
              << BatchNormalizationLayer(
@@ -704,7 +709,7 @@ private:
         SubStream i_d(graph);
         i_d << PoolingLayer(PoolingLayerInfo(PoolingType::AVG, 3, PadStrideInfo(1, 1, 1, 1, DimensionRoundingType::CEIL), true))
             << ConvolutionLayer(1U, 1U, 256U,
-                                get_weights_accessor(data_path, total_path + "Branch_3_Conv2d_0b_1x1_weights.npy"),
+                                get_weights_accessor(data_path, total_path + "Branch_3_Conv2d_0b_1x1_weights.npy", weights_layout),
                                 std::unique_ptr<arm_compute::graph::ITensorAccessor>(nullptr), PadStrideInfo(1, 1, 0, 0))
             << BatchNormalizationLayer(get_weights_accessor(data_path, total_path + "Branch_3_Conv2d_0b_1x1_BatchNorm_moving_mean.npy"),
                                        get_weights_accessor(data_path, total_path + "Branch_3_Conv2d_0b_1x1_BatchNorm_moving_variance.npy"),