arm_compute v18.08
diff --git a/examples/graph_googlenet.cpp b/examples/graph_googlenet.cpp
index 2dba67f..cdbb8d8 100644
--- a/examples/graph_googlenet.cpp
+++ b/examples/graph_googlenet.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;
@@ -36,74 +34,57 @@
/** Example demonstrating how to implement Googlenet'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 GraphGooglenetExample : public Example
{
public:
- void do_setup(int argc, char **argv) override
+ GraphGooglenetExample()
+ : cmd_parser(), common_opts(cmd_parser), common_params(), graph(0, "GoogleNet")
{
- 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;
+ }
+
+ // 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
const std::array<float, 3> mean_rgb{ { 122.68f, 116.67f, 104.01f } };
std::unique_ptr<IPreprocessor> preprocessor = arm_compute::support::cpp14::make_unique<CaffePreproccessor>(mean_rgb);
- // Set target. 0 (NEON), 1 (OpenCL), 2 (OpenCL with Tuner). 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(224U, 224U, 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(224U, 224U, 3U, 1U), DataType::F32),
- get_input_accessor(image, std::move(preprocessor)))
+ graph << common_params.target
+ << common_params.fast_math_hint
+ << InputLayer(input_descriptor, get_input_accessor(common_params, std::move(preprocessor)))
<< ConvolutionLayer(
7U, 7U, 64U,
- get_weights_accessor(data_path, "/cnn_data/googlenet_model/conv1/conv1_7x7_s2_w.npy"),
+ get_weights_accessor(data_path, "/cnn_data/googlenet_model/conv1/conv1_7x7_s2_w.npy", weights_layout),
get_weights_accessor(data_path, "/cnn_data/googlenet_model/conv1/conv1_7x7_s2_b.npy"),
PadStrideInfo(2, 2, 3, 3))
<< ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
@@ -111,41 +92,46 @@
<< NormalizationLayer(NormalizationLayerInfo(NormType::CROSS_MAP, 5, 0.0001f, 0.75f))
<< ConvolutionLayer(
1U, 1U, 64U,
- get_weights_accessor(data_path, "/cnn_data/googlenet_model/conv2/conv2_3x3_reduce_w.npy"),
+ get_weights_accessor(data_path, "/cnn_data/googlenet_model/conv2/conv2_3x3_reduce_w.npy", weights_layout),
get_weights_accessor(data_path, "/cnn_data/googlenet_model/conv2/conv2_3x3_reduce_b.npy"),
PadStrideInfo(1, 1, 0, 0))
<< ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
<< ConvolutionLayer(
3U, 3U, 192U,
- get_weights_accessor(data_path, "/cnn_data/googlenet_model/conv2/conv2_3x3_w.npy"),
+ get_weights_accessor(data_path, "/cnn_data/googlenet_model/conv2/conv2_3x3_w.npy", weights_layout),
get_weights_accessor(data_path, "/cnn_data/googlenet_model/conv2/conv2_3x3_b.npy"),
PadStrideInfo(1, 1, 1, 1))
<< ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
<< NormalizationLayer(NormalizationLayerInfo(NormType::CROSS_MAP, 5, 0.0001f, 0.75f))
<< PoolingLayer(PoolingLayerInfo(PoolingType::MAX, 3, PadStrideInfo(2, 2, 0, 0, DimensionRoundingType::CEIL)));
- graph << get_inception_node(data_path, "inception_3a", 64, std::make_tuple(96U, 128U), std::make_tuple(16U, 32U), 32U);
- graph << get_inception_node(data_path, "inception_3b", 128, std::make_tuple(128U, 192U), std::make_tuple(32U, 96U), 64U);
+ graph << get_inception_node(data_path, "inception_3a", weights_layout, 64, std::make_tuple(96U, 128U), std::make_tuple(16U, 32U), 32U);
+ graph << get_inception_node(data_path, "inception_3b", weights_layout, 128, std::make_tuple(128U, 192U), std::make_tuple(32U, 96U), 64U);
graph << PoolingLayer(PoolingLayerInfo(PoolingType::MAX, 3, PadStrideInfo(2, 2, 0, 0, DimensionRoundingType::CEIL)));
- graph << get_inception_node(data_path, "inception_4a", 192, std::make_tuple(96U, 208U), std::make_tuple(16U, 48U), 64U);
- graph << get_inception_node(data_path, "inception_4b", 160, std::make_tuple(112U, 224U), std::make_tuple(24U, 64U), 64U);
- graph << get_inception_node(data_path, "inception_4c", 128, std::make_tuple(128U, 256U), std::make_tuple(24U, 64U), 64U);
- graph << get_inception_node(data_path, "inception_4d", 112, std::make_tuple(144U, 288U), std::make_tuple(32U, 64U), 64U);
- graph << get_inception_node(data_path, "inception_4e", 256, std::make_tuple(160U, 320U), std::make_tuple(32U, 128U), 128U);
+ graph << get_inception_node(data_path, "inception_4a", weights_layout, 192, std::make_tuple(96U, 208U), std::make_tuple(16U, 48U), 64U);
+ graph << get_inception_node(data_path, "inception_4b", weights_layout, 160, std::make_tuple(112U, 224U), std::make_tuple(24U, 64U), 64U);
+ graph << get_inception_node(data_path, "inception_4c", weights_layout, 128, std::make_tuple(128U, 256U), std::make_tuple(24U, 64U), 64U);
+ graph << get_inception_node(data_path, "inception_4d", weights_layout, 112, std::make_tuple(144U, 288U), std::make_tuple(32U, 64U), 64U);
+ graph << get_inception_node(data_path, "inception_4e", weights_layout, 256, std::make_tuple(160U, 320U), std::make_tuple(32U, 128U), 128U);
graph << PoolingLayer(PoolingLayerInfo(PoolingType::MAX, 3, PadStrideInfo(2, 2, 0, 0, DimensionRoundingType::CEIL)));
- graph << get_inception_node(data_path, "inception_5a", 256, std::make_tuple(160U, 320U), std::make_tuple(32U, 128U), 128U);
- graph << get_inception_node(data_path, "inception_5b", 384, std::make_tuple(192U, 384U), std::make_tuple(48U, 128U), 128U);
+ graph << get_inception_node(data_path, "inception_5a", weights_layout, 256, std::make_tuple(160U, 320U), std::make_tuple(32U, 128U), 128U);
+ graph << get_inception_node(data_path, "inception_5b", weights_layout, 384, std::make_tuple(192U, 384U), std::make_tuple(48U, 128U), 128U);
graph << PoolingLayer(PoolingLayerInfo(PoolingType::AVG, 7, PadStrideInfo(1, 1, 0, 0, DimensionRoundingType::CEIL)))
<< FullyConnectedLayer(
1000U,
- get_weights_accessor(data_path, "/cnn_data/googlenet_model/loss3/loss3_classifier_w.npy"),
+ get_weights_accessor(data_path, "/cnn_data/googlenet_model/loss3/loss3_classifier_w.npy", weights_layout),
get_weights_accessor(data_path, "/cnn_data/googlenet_model/loss3/loss3_classifier_b.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);
+ 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
{
@@ -154,9 +140,12 @@
}
private:
- Stream graph{ 0, "GoogleNet" };
+ CommandLineParser cmd_parser;
+ CommonGraphOptions common_opts;
+ CommonGraphParams common_params;
+ Stream graph;
- BranchLayer get_inception_node(const std::string &data_path, std::string &¶m_path,
+ BranchLayer get_inception_node(const std::string &data_path, std::string &¶m_path, DataLayout weights_layout,
unsigned int a_filt,
std::tuple<unsigned int, unsigned int> b_filters,
std::tuple<unsigned int, unsigned int> c_filters,
@@ -166,7 +155,7 @@
SubStream i_a(graph);
i_a << ConvolutionLayer(
1U, 1U, a_filt,
- get_weights_accessor(data_path, total_path + "1x1_w.npy"),
+ get_weights_accessor(data_path, total_path + "1x1_w.npy", weights_layout),
get_weights_accessor(data_path, total_path + "1x1_b.npy"),
PadStrideInfo(1, 1, 0, 0))
<< ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU));
@@ -174,13 +163,13 @@
SubStream i_b(graph);
i_b << ConvolutionLayer(
1U, 1U, std::get<0>(b_filters),
- get_weights_accessor(data_path, total_path + "3x3_reduce_w.npy"),
+ get_weights_accessor(data_path, total_path + "3x3_reduce_w.npy", weights_layout),
get_weights_accessor(data_path, total_path + "3x3_reduce_b.npy"),
PadStrideInfo(1, 1, 0, 0))
<< ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
<< ConvolutionLayer(
3U, 3U, std::get<1>(b_filters),
- get_weights_accessor(data_path, total_path + "3x3_w.npy"),
+ get_weights_accessor(data_path, total_path + "3x3_w.npy", weights_layout),
get_weights_accessor(data_path, total_path + "3x3_b.npy"),
PadStrideInfo(1, 1, 1, 1))
<< ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU));
@@ -188,13 +177,13 @@
SubStream i_c(graph);
i_c << ConvolutionLayer(
1U, 1U, std::get<0>(c_filters),
- get_weights_accessor(data_path, total_path + "5x5_reduce_w.npy"),
+ get_weights_accessor(data_path, total_path + "5x5_reduce_w.npy", weights_layout),
get_weights_accessor(data_path, total_path + "5x5_reduce_b.npy"),
PadStrideInfo(1, 1, 0, 0))
<< ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU))
<< ConvolutionLayer(
5U, 5U, std::get<1>(c_filters),
- get_weights_accessor(data_path, total_path + "5x5_w.npy"),
+ get_weights_accessor(data_path, total_path + "5x5_w.npy", weights_layout),
get_weights_accessor(data_path, total_path + "5x5_b.npy"),
PadStrideInfo(1, 1, 2, 2))
<< ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU));
@@ -203,7 +192,7 @@
i_d << PoolingLayer(PoolingLayerInfo(PoolingType::MAX, 3, PadStrideInfo(1, 1, 1, 1, DimensionRoundingType::CEIL)))
<< ConvolutionLayer(
1U, 1U, d_filt,
- get_weights_accessor(data_path, total_path + "pool_proj_w.npy"),
+ get_weights_accessor(data_path, total_path + "pool_proj_w.npy", weights_layout),
get_weights_accessor(data_path, total_path + "pool_proj_b.npy"),
PadStrideInfo(1, 1, 0, 0))
<< ActivationLayer(ActivationLayerInfo(ActivationLayerInfo::ActivationFunction::RELU));
@@ -214,8 +203,10 @@
/** Main program for Googlenet
*
+ * @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)
{