arm_compute v18.08
diff --git a/examples/graph_inception_v4.cpp b/examples/graph_inception_v4.cpp
index ed95baa..b6c28b4 100644
--- a/examples/graph_inception_v4.cpp
+++ b/examples/graph_inception_v4.cpp
@@ -23,12 +23,10 @@
*/
#include "arm_compute/graph.h"
#include "support/ToolchainSupport.h"
+#include "utils/CommonGraphOptions.h"
#include "utils/GraphUtils.h"
#include "utils/Utils.h"
-#include <cstdlib>
-#include <tuple>
-
using namespace arm_compute::utils;
using namespace arm_compute::graph::frontend;
using namespace arm_compute::graph_utils;
@@ -36,76 +34,62 @@
/** Example demonstrating how to implement InceptionV4's network using the Compute Library's graph API
*
* @param[in] argc Number of arguments
- * @param[in] argv Arguments ( [optional] Target (0 = NEON, 1 = OpenCL, 2 = OpenCL with Tuner), [optional] Path to the weights folder, [optional] image, [optional] labels, [optional] Fast math for convolution layer (0 = DISABLED, 1 = ENABLED) )
+ * @param[in] argv Arguments
*/
class InceptionV4Example final : public Example
{
public:
- void do_setup(int argc, char **argv) override
+ InceptionV4Example()
+ : cmd_parser(), common_opts(cmd_parser), common_params(), graph(0, "InceptionV4")
{
- // Disabled the test for now because the process gets killed on Linux Firefly 32 bit even when using ConvolutionMethodHint::DIRECT.
- // Needs to review/rework to run the code below.
-#if __aarch64__
- std::string data_path; /* Path to the trainable data */
- std::string image; /* Image data */
- std::string label; /* Label data */
+ }
+ bool do_setup(int argc, char **argv) override
+ {
+ // Parse arguments
+ cmd_parser.parse(argc, argv);
+
+ // Consume common parameters
+ common_params = consume_common_graph_parameters(common_opts);
+
+ // Return when help menu is requested
+ if(common_params.help)
+ {
+ cmd_parser.print_help(argv[0]);
+ return false;
+ }
+
+ // Set default layout if needed
+ if(!common_opts.data_layout->is_set() && common_params.target == Target::NEON)
+ {
+ common_params.data_layout = DataLayout::NCHW;
+ }
+
+ // Checks
+ ARM_COMPUTE_EXIT_ON_MSG(arm_compute::is_data_type_quantized_asymmetric(common_params.data_type), "QASYMM8 not supported for this graph");
+ ARM_COMPUTE_EXIT_ON_MSG(common_params.data_type == DataType::F16 && common_params.target == Target::NEON, "F16 NEON not supported for this graph");
+
+ // Print parameter values
+ std::cout << common_params << std::endl;
+
+ // Get trainable parameters data path
+ std::string data_path = common_params.data_path;
// Create a preprocessor object
std::unique_ptr<IPreprocessor> preprocessor = arm_compute::support::cpp14::make_unique<TFPreproccessor>();
- // Set target. 0 (NEON), 1 (OpenCL). By default it is NEON
- const int target = argc > 1 ? std::strtol(argv[1], nullptr, 10) : 0;
- Target target_hint = set_target_hint(target);
- FastMathHint fast_math_hint = FastMathHint::DISABLED;
+ // 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);
- // Parse arguments
- if(argc < 2)
- {
- // Print help
- std::cout << "Usage: " << argv[0] << " [target] [path_to_data] [image] [labels] [fast_math_hint]\n\n";
- std::cout << "No data folder provided: using random values\n\n";
- }
- else if(argc == 2)
- {
- std::cout << "Usage: " << argv[0] << " " << argv[1] << " [path_to_data] [image] [labels] [fast_math_hint]\n\n";
- std::cout << "No data folder provided: using random values\n\n";
- }
- else if(argc == 3)
- {
- data_path = argv[2];
- std::cout << "Usage: " << argv[0] << " " << argv[1] << " " << argv[2] << " [image] [labels] [fast_math_hint]\n\n";
- std::cout << "No image provided: using random values\n\n";
- }
- else if(argc == 4)
- {
- data_path = argv[2];
- image = argv[3];
- std::cout << "Usage: " << argv[0] << " " << argv[1] << " " << argv[2] << " " << argv[3] << " [labels] [fast_math_hint]\n\n";
- std::cout << "No text file with labels provided: skipping output accessor\n\n";
- }
- else if(argc == 5)
- {
- data_path = argv[2];
- image = argv[3];
- label = argv[4];
- std::cout << "Usage: " << argv[0] << " " << argv[1] << " " << argv[2] << " " << argv[3] << " " << argv[4] << " [fast_math_hint]\n\n";
- std::cout << "No fast math info provided: disabling fast math\n\n";
- }
- else
- {
- data_path = argv[2];
- image = argv[3];
- label = argv[4];
- fast_math_hint = (std::strtol(argv[5], nullptr, 1) == 0) ? FastMathHint::DISABLED : FastMathHint::ENABLED;
- }
+ // Set weights trained layout
+ const DataLayout weights_layout = DataLayout::NCHW;
- graph << target_hint
- << fast_math_hint
- << InputLayer(TensorDescriptor(TensorShape(299U, 299U, 3U, 1U), DataType::F32),
- get_input_accessor(image, std::move(preprocessor), false))
+ graph << common_params.target
+ << common_params.fast_math_hint
+ << 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"),
@@ -115,7 +99,7 @@
<< 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"),
@@ -125,7 +109,7 @@
<< 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"),
@@ -134,62 +118,63 @@
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(label, 5));
+ << OutputLayer(get_output_accessor(common_params, 5));
// Finalize graph
GraphConfig config;
- config.use_tuner = (target == 2);
- graph.finalize(target_hint, config);
-#else /* __aarch64__ */
- using namespace arm_compute;
- ARM_COMPUTE_UNUSED(argc);
- ARM_COMPUTE_UNUSED(argv);
-#endif /* __aarch64__ */
+ config.num_threads = common_params.threads;
+ config.use_tuner = common_params.enable_tuner;
+ config.tuner_file = common_params.tuner_file;
+
+ graph.finalize(common_params.target, config);
+
+ return true;
}
void do_run() override
{
-#if __aarch64__
graph.run();
-#endif /* __aarch64__ */
}
private:
- Stream graph{ 0, "InceptionV4" };
+ CommandLineParser cmd_parser;
+ CommonGraphOptions common_opts;
+ CommonGraphParams common_params;
+ 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_";
@@ -198,7 +183,7 @@
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"),
@@ -210,13 +195,13 @@
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"),
@@ -225,7 +210,7 @@
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"),
@@ -236,7 +221,7 @@
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"),
@@ -245,7 +230,7 @@
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"),
@@ -254,7 +239,7 @@
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"),
@@ -263,7 +248,7 @@
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"),
@@ -275,13 +260,13 @@
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"),
@@ -296,13 +281,13 @@
return BranchLayer(BranchMergeMethod::DEPTH_CONCATENATE, std::move(i_a), std::move(i_b));
}
- BranchLayer get_inceptionA_block(const std::string &data_path, std::string &¶m_path)
+ BranchLayer get_inceptionA_block(const std::string &data_path, DataLayout weights_layout, std::string &¶m_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"),
@@ -313,7 +298,7 @@
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"),
@@ -322,7 +307,7 @@
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"),
@@ -333,7 +318,7 @@
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"),
@@ -342,7 +327,7 @@
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"),
@@ -351,7 +336,7 @@
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"),
@@ -363,7 +348,7 @@
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"),
@@ -375,13 +360,13 @@
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"),
@@ -392,7 +377,7 @@
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"),
@@ -401,7 +386,7 @@
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"),
@@ -410,7 +395,7 @@
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"),
@@ -425,13 +410,13 @@
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 &¶m_path)
+ BranchLayer get_inceptionB_block(const std::string &data_path, DataLayout weights_layout, std::string &¶m_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"),
@@ -442,7 +427,7 @@
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"),
@@ -451,7 +436,7 @@
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"),
@@ -460,7 +445,7 @@
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"),
@@ -471,7 +456,7 @@
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"),
@@ -480,7 +465,7 @@
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"),
@@ -489,7 +474,7 @@
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"),
@@ -498,7 +483,7 @@
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"),
@@ -507,7 +492,7 @@
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"),
@@ -519,7 +504,7 @@
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"),
@@ -531,13 +516,13 @@
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"),
@@ -546,7 +531,7 @@
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"),
@@ -557,7 +542,7 @@
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"),
@@ -566,7 +551,7 @@
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"),
@@ -575,7 +560,7 @@
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"),
@@ -584,7 +569,7 @@
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"),
@@ -599,13 +584,13 @@
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 &¶m_path)
+ BranchLayer get_inceptionC_block(const std::string &data_path, DataLayout weights_layout, std::string &¶m_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"),
@@ -617,7 +602,7 @@
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(
@@ -628,10 +613,10 @@
0.001f)
<< ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU));
- SubStream i_b1(static_cast<IStream &>(i_b));
+ 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(
@@ -642,10 +627,10 @@
0.001f)
<< ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU));
- SubStream i_b2(static_cast<IStream &>(i_b));
+ 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(
@@ -662,7 +647,7 @@
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(
@@ -674,7 +659,7 @@
<< 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(
@@ -686,7 +671,7 @@
<< 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(
@@ -697,10 +682,10 @@
0.001f)
<< ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU));
- SubStream i_c1(static_cast<IStream &>(i_c));
+ 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(
@@ -711,10 +696,10 @@
0.001f)
<< ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU));
- SubStream i_c2(static_cast<IStream &>(i_c));
+ 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(
@@ -731,7 +716,7 @@
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"),
@@ -746,8 +731,10 @@
/** Main program for Inception V4
*
+ * @note To list all the possible arguments execute the binary appended with the --help option
+ *
* @param[in] argc Number of arguments
- * @param[in] argv Arguments ( [optional] Target (0 = NEON, 1 = OpenCL, 2 = OpenCL with Tuner), [optional] Path to the weights folder, [optional] image, [optional] labels, [optional] Fast math for convolution layer (0 = DISABLED, 1 = ENABLED) )
+ * @param[in] argv Arguments
*/
int main(int argc, char **argv)
{