diff --git a/docs/OV_Runtime_UG/automatic_batching.md b/docs/OV_Runtime_UG/automatic_batching.md index 5b558502234..7fc4732a8e8 100644 --- a/docs/OV_Runtime_UG/automatic_batching.md +++ b/docs/OV_Runtime_UG/automatic_batching.md @@ -11,7 +11,7 @@ The Automatic Batching Execution mode (or Auto-batching for short) performs automatic batching on-the-fly to improve device utilization by grouping inference requests together, without programming effort from the user. With Automatic Batching, gathering the input and scattering the output from the individual inference requests required for the batch happen transparently, without affecting the application code. -Auto Batching can be used :ref:`directly as a virtual device ` or as an :ref:`option for inference on CPU/GPU/VPU ` (by means of configuration/hint). These 2 ways are provided for the user to enable the BATCH devices **explicitly** or **implicitly**, with the underlying logic remaining the same. An example of the difference is that the CPU device doesn’t support implicitly to enable BATCH device, commands such as ``./benchmark_app -m -d CPU -hint tput`` will not apply BATCH device **implicitly**, but ``./benchmark_app -m -d "BATCH:CPU(16)`` can **explicitly** load BATCH device. +Auto Batching can be used :ref:`directly as a virtual device ` or as an :ref:`option for inference on CPU/GPU/NPU ` (by means of configuration/hint). These 2 ways are provided for the user to enable the BATCH devices **explicitly** or **implicitly**, with the underlying logic remaining the same. An example of the difference is that the CPU device doesn’t support implicitly to enable BATCH device, commands such as ``./benchmark_app -m -d CPU -hint tput`` will not apply BATCH device **implicitly**, but ``./benchmark_app -m -d "BATCH:CPU(16)`` can **explicitly** load BATCH device. Auto-batching primarily targets the existing code written for inferencing many requests, each instance with the batch size 1. To get corresponding performance improvements, the application **must be running multiple inference requests simultaneously**. Auto-batching can also be used via a particular *virtual* device. diff --git a/docs/_static/download/operation_conformance_table_files/opset_report_omz_static.html b/docs/_static/download/operation_conformance_table_files/opset_report_omz_static.html index dea9f8ca231..4f95c22d048 100644 --- a/docs/_static/download/operation_conformance_table_files/opset_report_omz_static.html +++ b/docs/_static/download/operation_conformance_table_files/opset_report_omz_static.html @@ -105,7 +105,7 @@ GPU NVIDIA TEMPLATE - VPUX + NPU @@ -119,7 +119,7 @@ 95 95 95 - 93 + 93 @@ -131,7 +131,7 @@ 76.84 % 26.32 % 97.89 % - 11.83 % + 11.83 % @@ -143,7 +143,7 @@ 94.92 % 55.09 % 100.0 % - 21.1 % + 21.1 % @@ -155,7 +155,7 @@ 98.25 % 88.98 % 99.96 % - 7.69 % + 7.69 % @@ -304,12 +304,12 @@ - ---
@@ -430,12 +430,12 @@ - ---
@@ -556,12 +556,12 @@ - ---
@@ -682,12 +682,12 @@ - ---
@@ -808,12 +808,12 @@ - ---
@@ -969,12 +969,12 @@ - 0.0 %
@@ -1100,12 +1100,12 @@ - ---
@@ -1226,12 +1226,12 @@ - ---
@@ -1352,12 +1352,12 @@ - ---
@@ -1478,12 +1478,12 @@ - ---
@@ -1604,12 +1604,12 @@ - ---
@@ -1730,12 +1730,12 @@ - ---
@@ -1891,12 +1891,12 @@ - 0.0 %
@@ -2022,12 +2022,12 @@ - ---
@@ -2183,12 +2183,12 @@ - 0.0 %
@@ -2349,12 +2349,12 @@ - 0.0 %
@@ -2480,12 +2480,12 @@ - ---
@@ -2606,12 +2606,12 @@ - ---
@@ -2767,12 +2767,12 @@ - 0.0 %
@@ -2898,12 +2898,12 @@ - ---
@@ -3024,12 +3024,12 @@ - ---
@@ -3185,12 +3185,12 @@ - ---
@@ -3311,12 +3311,12 @@ - ---
@@ -3472,12 +3472,12 @@ - 0.0 %
@@ -3638,12 +3638,12 @@ - 0.0 %
@@ -3804,12 +3804,12 @@ - 0.0 %
@@ -3935,12 +3935,12 @@ - ---
@@ -4096,12 +4096,12 @@ - 0.0 %
@@ -4227,12 +4227,12 @@ - ---
@@ -4388,12 +4388,12 @@ - 0.0 %
@@ -4554,12 +4554,12 @@ - 0.0 %
@@ -4720,12 +4720,12 @@ - 0.0 %
@@ -4851,12 +4851,12 @@ - ---
@@ -5012,12 +5012,12 @@ - 0.0 %
@@ -5143,12 +5143,12 @@ - ---
@@ -5269,12 +5269,12 @@ - ---
@@ -5395,12 +5395,12 @@ - ---
@@ -5521,12 +5521,12 @@ - ---
@@ -5647,12 +5647,12 @@ - ---
@@ -5773,12 +5773,12 @@ - ---
@@ -5934,12 +5934,12 @@ - 0.0 %
@@ -6100,12 +6100,12 @@ - 0.0 %
@@ -6266,12 +6266,12 @@ - 75.0 %
@@ -6432,12 +6432,12 @@ - 0.0 %
@@ -6563,12 +6563,12 @@ - ---
@@ -6689,12 +6689,12 @@ - ---
@@ -6815,12 +6815,12 @@ - ---
@@ -6976,12 +6976,12 @@ - 0.0 %
@@ -7142,12 +7142,12 @@ - 0.0 %
@@ -7308,12 +7308,12 @@ - 0.0 %
@@ -7439,12 +7439,12 @@ - ---
@@ -7565,12 +7565,12 @@ - ---
@@ -7691,12 +7691,12 @@ - ---
@@ -7817,12 +7817,12 @@ - ---
@@ -7943,12 +7943,12 @@ - ---
@@ -8069,12 +8069,12 @@ - ---
@@ -8097,7 +8097,7 @@ N/A N/A N/A - N/A + N/A @@ -8244,12 +8244,12 @@ - 0.0 %
@@ -8410,12 +8410,12 @@ - 0.0 %
@@ -8576,12 +8576,12 @@ - 0.0 %
@@ -8707,12 +8707,12 @@ - ---
@@ -8833,12 +8833,12 @@ - ---
@@ -8994,12 +8994,12 @@ - 60.0 %
@@ -9160,12 +9160,12 @@ - 0.0 %
@@ -9291,12 +9291,12 @@ - ---
@@ -9452,12 +9452,12 @@ - 22.73 %
@@ -9583,12 +9583,12 @@ - ---
@@ -9709,12 +9709,12 @@ - ---
@@ -9870,12 +9870,12 @@ - 100.0 %
@@ -10001,12 +10001,12 @@ - ---
@@ -10127,12 +10127,12 @@ - ---
@@ -10288,12 +10288,12 @@ - 100.0 %
@@ -10419,12 +10419,12 @@ - ---
@@ -10580,12 +10580,12 @@ - 0.0 %
@@ -10711,12 +10711,12 @@ - ---
@@ -10837,12 +10837,12 @@ - ---
@@ -10998,12 +10998,12 @@ - 0.0 %
@@ -11164,12 +11164,12 @@ - 0.0 %
@@ -11295,7 +11295,7 @@ - N/A + N/A @@ -11442,12 +11442,12 @@ - 66.67 %
@@ -11608,12 +11608,12 @@ - 100.0 %
@@ -11774,12 +11774,12 @@ - 0.0 %
@@ -11905,12 +11905,12 @@ - ---
@@ -12031,12 +12031,12 @@ - ---
@@ -12192,12 +12192,12 @@ - 0.0 %
@@ -12323,12 +12323,12 @@ - ---
@@ -12484,12 +12484,12 @@ - 100.0 %
@@ -12615,12 +12615,12 @@ - ---
@@ -12741,12 +12741,12 @@ - ---
@@ -12902,12 +12902,12 @@ - 55.56 %
@@ -13033,12 +13033,12 @@ - ---
@@ -13159,12 +13159,12 @@ - ---
@@ -13285,12 +13285,12 @@ - ---
@@ -13446,12 +13446,12 @@ - 0.0 %
@@ -13577,12 +13577,12 @@ - ---
@@ -13703,12 +13703,12 @@ - ---
@@ -13829,12 +13829,12 @@ - ---
@@ -13990,12 +13990,12 @@ - 0.0 %
@@ -14121,12 +14121,12 @@ - ---
@@ -14247,12 +14247,12 @@ - ---
@@ -14408,12 +14408,12 @@ - 0.0 %
@@ -14574,12 +14574,12 @@ - 100.0 %
@@ -14705,12 +14705,12 @@ - ---
@@ -14866,12 +14866,12 @@ - 0.0 %
@@ -14997,12 +14997,12 @@ - ---
@@ -15123,12 +15123,12 @@ - ---
@@ -15249,12 +15249,12 @@ - ---
@@ -15375,12 +15375,12 @@ - ---
@@ -15536,12 +15536,12 @@ - 50.0 %
@@ -15702,12 +15702,12 @@ - 0.0 %
@@ -15833,12 +15833,12 @@ - ---
@@ -15959,12 +15959,12 @@ - ---
@@ -16120,12 +16120,12 @@ - 0.0 %
@@ -16286,12 +16286,12 @@ - 0.0 %
@@ -16452,12 +16452,12 @@ - 0.0 %
@@ -16618,12 +16618,12 @@ - 100.0 %
@@ -16749,12 +16749,12 @@ - ---
@@ -16875,12 +16875,12 @@ - ---
@@ -17001,12 +17001,12 @@ - ---
@@ -17162,12 +17162,12 @@ - 0.0 %
@@ -17293,12 +17293,12 @@ - ---
@@ -17419,12 +17419,12 @@ - ---
@@ -17580,12 +17580,12 @@ - 0.0 %
@@ -17711,12 +17711,12 @@ - ---
@@ -17837,12 +17837,12 @@ - ---
@@ -17963,12 +17963,12 @@ - ---
@@ -18089,12 +18089,12 @@ - ---
@@ -18215,12 +18215,12 @@ - ---
@@ -18341,12 +18341,12 @@ - ---
@@ -18502,12 +18502,12 @@ - 0.0 %
@@ -18668,12 +18668,12 @@ - ---
@@ -18794,12 +18794,12 @@ - ---
@@ -18955,12 +18955,12 @@ - 0.0 %
@@ -19086,12 +19086,12 @@ - ---
@@ -19247,12 +19247,12 @@ - 0.0 %
@@ -19378,7 +19378,7 @@ - N/A + N/A @@ -19490,12 +19490,12 @@ - ---
@@ -19651,12 +19651,12 @@ - 0.0 %
@@ -19782,12 +19782,12 @@ - ---
@@ -19908,12 +19908,12 @@ - ---
@@ -20034,12 +20034,12 @@ - ---
@@ -20160,12 +20160,12 @@ - ---
@@ -20321,12 +20321,12 @@ - 0.0 %
@@ -20452,12 +20452,12 @@ - ---
@@ -20578,12 +20578,12 @@ - ---
@@ -20704,12 +20704,12 @@ - ---
@@ -20830,12 +20830,12 @@ - ---
@@ -20956,12 +20956,12 @@ - ---
@@ -21117,12 +21117,12 @@ - 0.0 %
@@ -21248,12 +21248,12 @@ - ---
@@ -21374,12 +21374,12 @@ - ---
@@ -21500,12 +21500,12 @@ - ---
@@ -21626,12 +21626,12 @@ - ---
@@ -21752,12 +21752,12 @@ - ---
@@ -21878,12 +21878,12 @@ - ---
@@ -22004,12 +22004,12 @@ - 0.0 %
@@ -22135,12 +22135,12 @@ - ---
@@ -22261,12 +22261,12 @@ - ---
@@ -22422,12 +22422,12 @@ - 0.0 %
@@ -22588,12 +22588,12 @@ - 0.0 %
@@ -22754,12 +22754,12 @@ - 0.0 %
@@ -22920,12 +22920,12 @@ - 0.0 %
@@ -23086,12 +23086,12 @@ - 0.0 %
@@ -23252,12 +23252,12 @@ - 0.0 %
@@ -23418,12 +23418,12 @@ - 0.0 %
@@ -23549,12 +23549,12 @@ - ---
@@ -23710,12 +23710,12 @@ - 0.0 %
@@ -23841,12 +23841,12 @@ - ---
@@ -23967,12 +23967,12 @@ - ---
@@ -24093,12 +24093,12 @@ - ---
@@ -24219,12 +24219,12 @@ - ---
@@ -24380,12 +24380,12 @@ - 0.0 %
@@ -24511,7 +24511,7 @@ - N/A + N/A @@ -24658,12 +24658,12 @@ - 0.0 %
@@ -24824,12 +24824,12 @@ - 0.0 %
@@ -24990,12 +24990,12 @@ - 0.0 %
@@ -25156,12 +25156,12 @@ - 0.0 %
@@ -25287,12 +25287,12 @@ - ---
@@ -25448,12 +25448,12 @@ - 100.0 %
@@ -25614,12 +25614,12 @@ - 75.0 %
@@ -25780,12 +25780,12 @@ - 100.0 %
@@ -25946,12 +25946,12 @@ - 0.0 %
@@ -26077,12 +26077,12 @@ - ---
@@ -26238,12 +26238,12 @@ - 0.0 %
@@ -26369,12 +26369,12 @@ - ---
@@ -26530,12 +26530,12 @@ - 90.91 %
@@ -26696,12 +26696,12 @@ - 100.0 %
@@ -26827,12 +26827,12 @@ - ---
@@ -26988,12 +26988,12 @@ - 0.0 %
@@ -27154,12 +27154,12 @@ - 44.44 %
@@ -27320,12 +27320,12 @@ - 0.0 %
@@ -27486,12 +27486,12 @@ - 0.0 %
@@ -27652,12 +27652,12 @@ - 0.0 %
@@ -27818,12 +27818,12 @@ - 0.0 %
@@ -27949,12 +27949,12 @@ - ---
@@ -28110,12 +28110,12 @@ - 0.0 %
@@ -28276,12 +28276,12 @@ - 0.0 %
@@ -28442,12 +28442,12 @@ - 22.22 %
@@ -28608,12 +28608,12 @@ - 100.0 %
@@ -28739,12 +28739,12 @@ - ---
@@ -28900,12 +28900,12 @@ - 100.0 %
@@ -29031,12 +29031,12 @@ - ---
@@ -29192,12 +29192,12 @@ - 50.0 %
@@ -29323,12 +29323,12 @@ - ---
@@ -29449,12 +29449,12 @@ - ---
@@ -29610,12 +29610,12 @@ - 25.0 %
@@ -29776,12 +29776,12 @@ - 71.43 %
@@ -29907,12 +29907,12 @@ - ---
@@ -30068,12 +30068,12 @@ - 63.64 %
@@ -30234,12 +30234,12 @@ - 90.0 %
@@ -30365,12 +30365,12 @@ - ---
diff --git a/docs/optimization_guide/nncf/ptq/basic_quantization_flow.md b/docs/optimization_guide/nncf/ptq/basic_quantization_flow.md index 5fc93dcc344..2b31176f1ef 100644 --- a/docs/optimization_guide/nncf/ptq/basic_quantization_flow.md +++ b/docs/optimization_guide/nncf/ptq/basic_quantization_flow.md @@ -191,7 +191,7 @@ Tune quantization parameters regex = '.*layer_.*' nncf.quantize(model, dataset, ignored_scope=nncf.IgnoredScope(patterns=regex)) -* ``target_device`` - defines the target device, the specificity of which will be taken into account during optimization. The following values are supported: ``ANY`` (default), ``CPU``, ``CPU_SPR``, ``GPU``, and ``VPU``. +* ``target_device`` - defines the target device, the specificity of which will be taken into account during optimization. The following values are supported: ``ANY`` (default), ``CPU``, ``CPU_SPR``, ``GPU``, and ``NPU``. .. code-block:: sh diff --git a/samples/cpp/speech_sample/README.md b/samples/cpp/speech_sample/README.md index 4ce550c1c34..188a5b43cbc 100644 --- a/samples/cpp/speech_sample/README.md +++ b/samples/cpp/speech_sample/README.md @@ -96,7 +96,7 @@ Several execution modes are supported via the ``-d`` flag: - ``CPU`` - All calculations are performed on CPU device using CPU Plugin. - ``GPU`` - All calculations are performed on GPU device using GPU Plugin. -- ``VPUX`` - All calculations are performed on VPUX device using VPUX Plugin. +- ``NPU`` - All calculations are performed on NPU device using NPU Plugin. - ``GNA_AUTO`` - GNA hardware is used if available and the driver is installed. Otherwise, the GNA device is emulated in fast-but-not-bit-exact mode. - ``GNA_HW`` - GNA hardware is used if available and the driver is installed. Otherwise, an error will occur. - ``GNA_SW`` - Deprecated. The GNA device is emulated in fast-but-not-bit-exact mode. @@ -144,7 +144,7 @@ Usage message: -i "" Required. Path(s) to input file(s). Usage for a single file/layer: or . Example of usage for several files/layers: :=,:=. -m "" Required. Path to an .xml file with a trained model (required if -rg is missing). -o "" Optional. Output file name(s) to save scores (inference results). Example of usage for a single file/layer: or . Example of usage for several files/layers: :=,:=. - -d "" Optional. Specify a target device to infer on. CPU, GPU, VPUX, GNA_AUTO, GNA_HW, GNA_HW_WITH_SW_FBACK, GNA_SW_FP32, GNA_SW_EXACT and HETERO with combination of GNA as the primary device and CPU as a secondary (e.g. HETERO:GNA,CPU) are supported. The sample will look for a suitable plugin for device specified. + -d "" Optional. Specify a target device to infer on. CPU, GPU, NPU, GNA_AUTO, GNA_HW, GNA_HW_WITH_SW_FBACK, GNA_SW_FP32, GNA_SW_EXACT and HETERO with combination of GNA as the primary device and CPU as a secondary (e.g. HETERO:GNA,CPU) are supported. The sample will look for a suitable plugin for device specified. -pc Optional. Enables per-layer performance report. -q "" Optional. Input quantization mode for GNA: static (default) or user defined (use with -sf). -qb "" Optional. Weight resolution in bits for GNA quantization: 8 or 16 (default) @@ -162,7 +162,7 @@ Usage message: -compile_target "" Optional. Specify GNA compile target generation. May be one of GNA_TARGET_2_0, GNA_TARGET_3_0. By default, generation corresponds to the GNA HW available in the system or the latest fully supported generation by the software. See the GNA Plugin's GNA_COMPILE_TARGET config option description. -memory_reuse_off Optional. Disables memory optimizations for compiled model. - Available target devices: CPU GNA GPU VPUX + Available target devices: CPU GNA GPU NPU .. _model-preparation-speech: diff --git a/samples/cpp/speech_sample/speech_sample.hpp b/samples/cpp/speech_sample/speech_sample.hpp index 4445e7e3442..0bc3a24c950 100644 --- a/samples/cpp/speech_sample/speech_sample.hpp +++ b/samples/cpp/speech_sample/speech_sample.hpp @@ -24,7 +24,7 @@ static const char model_message[] = "Required. Path to an .xml file with a train /// @brief message for assigning calculation to device static const char target_device_message[] = - "Optional. Specify a target device to infer on. CPU, GPU, VPUX, GNA_AUTO, GNA_HW, " + "Optional. Specify a target device to infer on. CPU, GPU, NPU, GNA_AUTO, GNA_HW, " "GNA_HW_WITH_SW_FBACK, GNA_SW_FP32, " "GNA_SW_EXACT and HETERO with combination of GNA as the primary device and CPU" " as a secondary (e.g. HETERO:GNA,CPU) are supported. " @@ -274,7 +274,7 @@ bool parse_and_check_command_line(int argc, char* argv[]) { "HETERO:GNA_HW,CPU", "HETERO:GNA_SW_EXACT,CPU", "HETERO:GNA_SW_FP32,CPU", - "VPUX"}; + "NPU"}; if (std::find(supportedDevices.begin(), supportedDevices.end(), FLAGS_d) == supportedDevices.end()) { throw std::logic_error("Specified device is not supported."); diff --git a/samples/python/speech_sample/README.md b/samples/python/speech_sample/README.md index c535b735e90..5eb431d8734 100644 --- a/samples/python/speech_sample/README.md +++ b/samples/python/speech_sample/README.md @@ -95,7 +95,7 @@ Several execution modes are supported via the ``-d`` flag: - ``CPU`` - All calculations are performed on CPU device using CPU Plugin. - ``GPU`` - All calculations are performed on GPU device using GPU Plugin. -- ``VPUX`` - All calculations are performed on VPUX device using VPUX Plugin. +- ``NPU`` - All calculations are performed on NPU device using NPU Plugin. - ``GNA_AUTO`` - GNA hardware is used if available and the driver is installed. Otherwise, the GNA device is emulated in fast-but-not-bit-exact mode. - ``GNA_HW`` - GNA hardware is used if available and the driver is installed. Otherwise, an error will occur. - ``GNA_SW`` - Deprecated. The GNA device is emulated in fast-but-not-bit-exact mode. @@ -155,7 +155,7 @@ Usage message: Usage for a single file/layer: or . Example of usage for several files/layers: :=,:=. -d DEVICE, --device DEVICE - Optional. Specify a target device to infer on. CPU, GPU, VPUX, GNA_AUTO, GNA_HW, GNA_SW_FP32, + Optional. Specify a target device to infer on. CPU, GPU, NPU, GNA_AUTO, GNA_HW, GNA_SW_FP32, GNA_SW_EXACT and HETERO with combination of GNA as the primary device and CPU as a secondary (e.g. HETERO:GNA,CPU) are supported. The sample will look for a suitable plugin for device specified. Default value is CPU. diff --git a/samples/python/speech_sample/arg_parser.py b/samples/python/speech_sample/arg_parser.py index 64da5cc3425..c498eb286df 100644 --- a/samples/python/speech_sample/arg_parser.py +++ b/samples/python/speech_sample/arg_parser.py @@ -32,7 +32,7 @@ def build_arg_parser() -> argparse.ArgumentParser: 'Example of usage for several files/layers: :=,:=.') args.add_argument('-d', '--device', default='CPU', type=str, help='Optional. Specify a target device to infer on. ' - 'CPU, GPU, VPUX, GNA_AUTO, GNA_HW, GNA_SW_FP32, GNA_SW_EXACT and HETERO with combination of GNA' + 'CPU, GPU, NPU, GNA_AUTO, GNA_HW, GNA_SW_FP32, GNA_SW_EXACT and HETERO with combination of GNA' ' as the primary device and CPU as a secondary (e.g. HETERO:GNA,CPU) are supported. ' 'The sample will look for a suitable plugin for device specified. Default value is CPU.') args.add_argument('-bs', '--batch_size', type=int, choices=range(1, 9), metavar='[1-8]', diff --git a/src/inference/include/ie/vpu/myriad_config.hpp b/src/inference/include/ie/vpu/myriad_config.hpp index 092fea346e2..641b4d1dbf1 100644 --- a/src/inference/include/ie/vpu/myriad_config.hpp +++ b/src/inference/include/ie/vpu/myriad_config.hpp @@ -50,7 +50,7 @@ DECLARE_VPU_CONFIG(MYRIAD_PCIE); DECLARE_VPU_CONFIG(MYRIAD_USB); /** - * @brief Optimize vpu plugin execution to maximize throughput. + * @brief Optimize MYRIAD plugin execution to maximize throughput. * This option should be used with integer value which is the requested number of streams. * The only possible values are: * 1 diff --git a/src/plugins/auto/src/auto_executable_network.cpp b/src/plugins/auto/src/auto_executable_network.cpp index aad0ea5c3a2..7288a8d8e33 100644 --- a/src/plugins/auto/src/auto_executable_network.cpp +++ b/src/plugins/auto/src/auto_executable_network.cpp @@ -215,7 +215,7 @@ IE::Parameter AutoExecutableNetwork::GetMetric(const std::string& name) const { iie.what()); } real = (std::max)(requests, optimalBatchSize); - } else if (deviceInfo.deviceName.find("VPUX") != std::string::npos) { + } else if (deviceInfo.deviceName.find("NPU") != std::string::npos) { real = 8u; } else { real = upperBoundStreamsNum ? 2 * upperBoundStreamsNum : defaultNumForTPUT; diff --git a/src/plugins/auto/src/auto_schedule.cpp b/src/plugins/auto/src/auto_schedule.cpp index f648b2ce497..585a39ef709 100644 --- a/src/plugins/auto/src/auto_schedule.cpp +++ b/src/plugins/auto/src/auto_schedule.cpp @@ -644,10 +644,10 @@ void AutoSchedule::TryToLoadNetWork(AutoLoadContext& context, const std::string& } // need to reload network, unregister it's priority // there maybe potential issue. - // for example they are dGPU, VPUX, iGPU, customer want to LoadNetwork with - // configure 0 dGPU, 1 VPUX, if dGPU load failed, - // the result will be not sure, maybe two network are loaded into VPUX, - // maybe 0 is loaded to VPUX, 1 is loaded to iGPU + // for example they are dGPU, NPU, iGPU, customer want to LoadNetwork with + // configure 0 dGPU, 1 NPU, if dGPU load failed, + // the result will be not sure, maybe two network are loaded into NPU, + // maybe 0 is loaded to NPU, 1 is loaded to iGPU _autoSContext->_plugin->UnregisterPriority(_autoSContext->_modelPriority, context.deviceInfo.uniqueName); // remove the current device from deviceList auto eraseDevice = deviceChecker().checkAndReturnIfDeviceInList(device, deviceList, true); diff --git a/src/plugins/auto/src/plugin.cpp b/src/plugins/auto/src/plugin.cpp index 5719d87072b..2227fd6e445 100644 --- a/src/plugins/auto/src/plugin.cpp +++ b/src/plugins/auto/src/plugin.cpp @@ -533,7 +533,7 @@ std::list MultiDeviceInferencePlugin::GetValidDevice( std::list dGPU; std::list iGPU; std::list MYRIAD; - std::list VPUX; + std::list NPU; for (auto& item : metaDevices) { if (item.deviceName.find("CPU") == 0) { @@ -544,8 +544,8 @@ std::list MultiDeviceInferencePlugin::GetValidDevice( MYRIAD.push_back(item); continue; } - if (item.deviceName.find("VPUX") == 0) { - VPUX.push_back(item); + if (item.deviceName.find("NPU") == 0) { + NPU.push_back(item); continue; } if (item.deviceName.find("GPU") == 0) { @@ -566,14 +566,14 @@ std::list MultiDeviceInferencePlugin::GetValidDevice( } } - // Priority of selecting device: dGPU > VPUX > iGPU > MYRIAD > CPU + // Priority of selecting device: dGPU > NPU > iGPU > MYRIAD > CPU std::list devices; if (networkPrecision == "INT8") { - devices.splice(devices.end(), VPUX); + devices.splice(devices.end(), NPU); devices.splice(devices.end(), dGPU); } else { devices.splice(devices.end(), dGPU); - devices.splice(devices.end(), VPUX); + devices.splice(devices.end(), NPU); } devices.splice(devices.end(), iGPU); devices.splice(devices.end(), MYRIAD); diff --git a/src/plugins/auto/src/plugin_config.cpp b/src/plugins/auto/src/plugin_config.cpp index bf9fd5de075..a9208362d07 100644 --- a/src/plugins/auto/src/plugin_config.cpp +++ b/src/plugins/auto/src/plugin_config.cpp @@ -7,7 +7,7 @@ namespace MultiDevicePlugin { // AUTO will enable the blocklist if // 1.No device priority passed to AUTO/MULTI.(eg. core.compile_model(model, "AUTO", configs);) // 2.No valid device parsed out from device priority (eg. core.compile_model(model, "AUTO:-CPU,-GPU", configs);). -const std::set PluginConfig::_deviceBlocklist = {"VPUX", "GNA", "notIntelGPU"}; +const std::set PluginConfig::_deviceBlocklist = {"NPU", "GNA", "notIntelGPU"}; PluginConfig::PluginConfig() { set_default(); diff --git a/src/plugins/auto/tests/unit/auto_runtime_fallback_test.cpp b/src/plugins/auto/tests/unit/auto_runtime_fallback_test.cpp index db2b323506e..8beda21b51c 100644 --- a/src/plugins/auto/tests/unit/auto_runtime_fallback_test.cpp +++ b/src/plugins/auto/tests/unit/auto_runtime_fallback_test.cpp @@ -43,27 +43,27 @@ public: ov::SoPtr mockExeNetwork; ov::SoPtr mockExeNetworkGPU_0; ov::SoPtr mockExeNetworkGPU_1; - ov::SoPtr mockExeNetworkVPUX; + ov::SoPtr mockExeNetworkNPU; std::shared_ptr> inferReqInternal; std::shared_ptr> inferReqInternalGPU_0; std::shared_ptr> inferReqInternalGPU_1; - std::shared_ptr> inferReqInternalVPUX; + std::shared_ptr> inferReqInternalNPU; std::shared_ptr> mockIExeNet; std::shared_ptr> mockIExeNetGPU_0; std::shared_ptr> mockIExeNetGPU_1; - std::shared_ptr> mockIExeNetVPUX; + std::shared_ptr> mockIExeNetNPU; std::shared_ptr mockInferrequest; std::shared_ptr mockInferrequestGPU_0; std::shared_ptr mockInferrequestGPU_1; - std::shared_ptr mockInferrequestVPUX; + std::shared_ptr mockInferrequestNPU; std::shared_ptr mockExecutor; std::shared_ptr mockExecutorGPU_0; std::shared_ptr mockExecutorGPU_1; - std::shared_ptr mockExecutorVPUX; + std::shared_ptr mockExecutorNPU; size_t optimalNum; @@ -110,19 +110,19 @@ public: inferReqInternal.reset(); inferReqInternalGPU_0.reset(); inferReqInternalGPU_1.reset(); - inferReqInternalVPUX.reset(); + inferReqInternalNPU.reset(); mockIExeNet.reset(); mockIExeNetGPU_0.reset(); mockIExeNetGPU_1.reset(); - mockIExeNetVPUX.reset(); + mockIExeNetNPU.reset(); mockIExeNet.reset(); mockIExeNetGPU_0.reset(); mockIExeNetGPU_1.reset(); - mockIExeNetVPUX.reset(); + mockIExeNetNPU.reset(); mockExecutor.reset(); mockExecutorGPU_0.reset(); mockExecutorGPU_1.reset(); - mockExecutorVPUX.reset(); + mockExecutorNPU.reset(); } void SetUp() override { @@ -136,8 +136,8 @@ public: mockIExeNetGPU_1 = std::make_shared>(); mockExeNetworkGPU_1 = {mockIExeNetGPU_1, {}}; - mockIExeNetVPUX = std::make_shared>(); - mockExeNetworkVPUX = {mockIExeNetVPUX, {}}; + mockIExeNetNPU = std::make_shared>(); + mockExeNetworkNPU = {mockIExeNetNPU, {}}; // prepare mockicore and cnnNetwork for loading core = std::make_shared>(); @@ -150,7 +150,7 @@ public: IE_SET_METRIC(SUPPORTED_CONFIG_KEYS, supportConfigs, {}); ON_CALL(*core, GetMetric(_, StrEq(METRIC_KEY(SUPPORTED_CONFIG_KEYS)), _)).WillByDefault(Return(supportConfigs)); ON_CALL(*core, GetConfig(_, StrEq(ov::compilation_num_threads.name()))).WillByDefault(Return(12)); - std::vector availableDevs = {"CPU", "GPU.0", "GPU.1", "VPUX"}; + std::vector availableDevs = {"CPU", "GPU.0", "GPU.1", "NPU"}; ON_CALL(*core, GetAvailableDevices()).WillByDefault(Return(availableDevs)); std::vector metrics = {METRIC_KEY(SUPPORTED_CONFIG_KEYS)}; @@ -173,7 +173,7 @@ public: ::testing::Matcher(StrEq(CommonTestUtils::DEVICE_KEEMBAY)), ::testing::Matcher(_))).WillByDefault(InvokeWithoutArgs([this]() { std::this_thread::sleep_for(std::chrono::milliseconds(200)); - return mockExeNetworkVPUX; })); + return mockExeNetworkNPU; })); ON_CALL(*core, LoadNetwork(::testing::Matcher(_), ::testing::Matcher(StrEq(CommonTestUtils::DEVICE_CPU)), @@ -224,9 +224,9 @@ public: ON_CALL(*mockIExeNetGPU_1.get(), GetMetric(StrEq(METRIC_KEY(OPTIMAL_NUMBER_OF_INFER_REQUESTS)))) .WillByDefault(Return(optimalNum)); - inferReqInternalVPUX = std::make_shared>(); - mockExecutorVPUX = std::make_shared(); - ON_CALL(*mockIExeNetVPUX.get(), GetMetric(StrEq(METRIC_KEY(OPTIMAL_NUMBER_OF_INFER_REQUESTS)))) + inferReqInternalNPU = std::make_shared>(); + mockExecutorNPU = std::make_shared(); + ON_CALL(*mockIExeNetNPU.get(), GetMetric(StrEq(METRIC_KEY(OPTIMAL_NUMBER_OF_INFER_REQUESTS)))) .WillByDefault(Return(optimalNum)); } }; @@ -275,12 +275,12 @@ TEST_P(AutoRuntimeFallback, releaseResource) { std::this_thread::sleep_for(std::chrono::milliseconds(0)); return mockInferrequestGPU_1; })); } - } else if (deviceName == "VPUX") { - mockInferrequestVPUX = std::make_shared( - inferReqInternalVPUX, mockExecutorVPUX, nullptr, ifThrow); - ON_CALL(*mockIExeNetVPUX.get(), CreateInferRequest()).WillByDefault(InvokeWithoutArgs([this]() { + } else if (deviceName == "NPU") { + mockInferrequestNPU = std::make_shared( + inferReqInternalNPU, mockExecutorNPU, nullptr, ifThrow); + ON_CALL(*mockIExeNetNPU.get(), CreateInferRequest()).WillByDefault(InvokeWithoutArgs([this]() { std::this_thread::sleep_for(std::chrono::milliseconds(0)); - return mockInferrequestVPUX; })); + return mockInferrequestNPU; })); } else { return; } @@ -321,10 +321,10 @@ const std::vector testConfigs = { ConfigParams{{{"GPU.0", false}, {"CPU", true}}, 2, true, false, false, false}, ConfigParams{{{"GPU.0", true}, {"CPU", true}}, 2, true, true, false, false}, // 3 devices - ConfigParams{{{"GPU.0", false}, {"GPU.1", false}, {"VPUX", false}}, 1, true, false, false, false}, - ConfigParams{{{"GPU.0", true}, {"GPU.1", false}, {"VPUX", false}}, 2, true, false, false, false}, - ConfigParams{{{"GPU.0", true}, {"GPU.1", true}, {"VPUX", false}}, 3, true, false, false, false}, - ConfigParams{{{"GPU.0", true}, {"GPU.1", true}, {"VPUX", true}}, 3, true, true, false, false}, + ConfigParams{{{"GPU.0", false}, {"GPU.1", false}, {"NPU", false}}, 1, true, false, false, false}, + ConfigParams{{{"GPU.0", true}, {"GPU.1", false}, {"NPU", false}}, 2, true, false, false, false}, + ConfigParams{{{"GPU.0", true}, {"GPU.1", true}, {"NPU", false}}, 3, true, false, false, false}, + ConfigParams{{{"GPU.0", true}, {"GPU.1", true}, {"NPU", true}}, 3, true, true, false, false}, //CPU_HELP does not throw ConfigParams{{{"GPU.0", false}, {"GPU.1", false}, {"CPU", false}}, 2, true, false, false, false}, ConfigParams{{{"GPU.0", true}, {"GPU.1", false}, {"CPU", false}}, 2, true, false, false, false}, @@ -345,10 +345,10 @@ const std::vector testConfigs = { ConfigParams{{{"GPU.0", false}, {"CPU", true}}, 2, false, true, false, false}, ConfigParams{{{"GPU.0", true}, {"CPU", true}}, 2, false, true, false, false}, // 3 devices - ConfigParams{{{"GPU.0", false}, {"GPU.1", false}, {"VPUX", false}}, 1, false, false, false, false}, - ConfigParams{{{"GPU.0", true}, {"GPU.1", false}, {"VPUX", false}}, 1, false, true, false, false}, - ConfigParams{{{"GPU.0", true}, {"GPU.1", true}, {"VPUX", false}}, 1, false, true, false, false}, - ConfigParams{{{"GPU.0", true}, {"GPU.1", true}, {"VPUX", true}}, 1, false, true, false, false}, + ConfigParams{{{"GPU.0", false}, {"GPU.1", false}, {"NPU", false}}, 1, false, false, false, false}, + ConfigParams{{{"GPU.0", true}, {"GPU.1", false}, {"NPU", false}}, 1, false, true, false, false}, + ConfigParams{{{"GPU.0", true}, {"GPU.1", true}, {"NPU", false}}, 1, false, true, false, false}, + ConfigParams{{{"GPU.0", true}, {"GPU.1", true}, {"NPU", true}}, 1, false, true, false, false}, //CPU_HELP does not throw ConfigParams{{{"GPU.0", false}, {"GPU.1", false}, {"CPU", false}}, 2, false, false, false, false}, ConfigParams{{{"GPU.0", true}, {"GPU.1", false}, {"CPU", false}}, 2, false, false, false, false}, @@ -358,8 +358,8 @@ const std::vector testConfigs = { ConfigParams{{{"GPU.0", true}, {"GPU.1", false}, {"CPU", true}}, 2, false, true, false, false}, ConfigParams{{{"GPU.0", true}, {"GPU.1", true}, {"CPU", true}}, 2, false, true, false, false}, // loadFail and CreateInferRequestFail - ConfigParams{{{"GPU.0", true}, {"GPU.1", false}, {"VPUX", false}}, 3, true, false, true, false}, - ConfigParams{{{"GPU.0", true}, {"GPU.1", false}, {"VPUX", false}}, 3, true, false, false, true}, + ConfigParams{{{"GPU.0", true}, {"GPU.1", false}, {"NPU", false}}, 3, true, false, true, false}, + ConfigParams{{{"GPU.0", true}, {"GPU.1", false}, {"NPU", false}}, 3, true, false, false, true}, }; INSTANTIATE_TEST_SUITE_P(smoke_AutoRuntimeFallback, AutoRuntimeFallback, diff --git a/src/plugins/auto/tests/unit/auto_select_device_failed_test.cpp b/src/plugins/auto/tests/unit/auto_select_device_failed_test.cpp index 9aecef4aee4..95c5c828510 100644 --- a/src/plugins/auto/tests/unit/auto_select_device_failed_test.cpp +++ b/src/plugins/auto/tests/unit/auto_select_device_failed_test.cpp @@ -217,7 +217,7 @@ TEST_P(AutoLoadFailedTest, LoadCNNetWork) { metaDevices.push_back(std::move(devInfo)); // set the return value of SelectDevice - // for example if there are three device, if will return GPU on the first call, and then MYRIAD + // for example if there are three device, if will return GPU on the first call, and then NPU // at last CPU ON_CALL(*plugin, SelectDevice(Property(&std::vector::size, Eq(selDevsSize)), _, _)) .WillByDefault(Return(metaDevices[deviceConfigs.size() - selDevsSize])); @@ -272,12 +272,12 @@ TEST_P(AutoLoadFailedTest, LoadCNNetWork) { // { true, false, GENERAL, 3 device, 2, 3, 2} // // there are three devices for loading -// CPU load for accelerator success, but GPU will load faild and then select MYRIAD and load again +// CPU load for accelerator success, but GPU will load faild and then select NPU and load again // LoadExeNetworkImpl will not throw exception and can continue to run, -// it will select twice, first select GPU, second select MYRIAD -// it will load network three times(CPU, GPU, MYRIAD) +// it will select twice, first select GPU, second select NPU +// it will load network three times(CPU, GPU, NPU) // the inference request num is loadSuccessCount * optimalNum, in this test case optimalNum is 2 -// so inference request num is 4 (CPU 2, MYRIAD 2) +// so inference request num is 4 (CPU 2, NPU 2) // const std::vector testConfigs = {ConfigParams {true, false, GENERAL, {DeviceParams {CommonTestUtils::DEVICE_GPU, true}, DeviceParams {CommonTestUtils::DEVICE_KEEMBAY, true}, diff --git a/src/plugins/auto/tests/unit/exec_network_get_metrics.cpp b/src/plugins/auto/tests/unit/exec_network_get_metrics.cpp index 75d15c10e5f..8ca7f637c06 100644 --- a/src/plugins/auto/tests/unit/exec_network_get_metrics.cpp +++ b/src/plugins/auto/tests/unit/exec_network_get_metrics.cpp @@ -254,12 +254,12 @@ TEST_P(ExecNetworkGetMetricOptimalNumInferReq, OPTIMAL_NUMBER_OF_INFER_REQUESTS) InferenceEngine::PluginConfigParams::THROUGHPUT}}, actualCustomerNum, ""}); // enable autoBatch IE_SET_METRIC(OPTIMAL_BATCH_SIZE, gpuOptimalBatchNum, 8); - IE_SET_METRIC(OPTIMAL_BATCH_SIZE, keembayOptimalBatchNum, 1); + IE_SET_METRIC(OPTIMAL_BATCH_SIZE, npuOptimalBatchNum, 1); IE_SET_METRIC(RANGE_FOR_STREAMS, rangeOfStreams, std::make_tuple(1, 3)); ON_CALL(*core.get(), GetMetric(StrEq(CommonTestUtils::DEVICE_GPU), StrEq(METRIC_KEY(OPTIMAL_BATCH_SIZE)), _)) .WillByDefault(RETURN_MOCK_VALUE(gpuOptimalBatchNum)); ON_CALL(*core.get(), GetMetric(StrEq(CommonTestUtils::DEVICE_KEEMBAY), StrEq(METRIC_KEY(OPTIMAL_BATCH_SIZE)), _)) - .WillByDefault(RETURN_MOCK_VALUE(keembayOptimalBatchNum)); + .WillByDefault(RETURN_MOCK_VALUE(npuOptimalBatchNum)); ON_CALL(*core.get(), GetMetric(_, StrEq(METRIC_KEY(RANGE_FOR_STREAMS)), _)) .WillByDefault(RETURN_MOCK_VALUE(rangeOfStreams)); ON_CALL(*core.get(), GetConfig(_, StrEq(CONFIG_KEY(PERFORMANCE_HINT)))) diff --git a/src/plugins/auto/tests/unit/get_device_list.cpp b/src/plugins/auto/tests/unit/get_device_list.cpp index 143e64ccf96..984af16e5c4 100644 --- a/src/plugins/auto/tests/unit/get_device_list.cpp +++ b/src/plugins/auto/tests/unit/get_device_list.cpp @@ -32,8 +32,8 @@ using ::testing::_; using Config = std::map; using namespace MockMultiDevice; -const std::vector availableDevs = {"CPU", "GPU", "VPUX"}; -const std::vector availableDevsWithId = {"CPU", "GPU.0", "GPU.1", "VPUX"}; +const std::vector availableDevs = {"CPU", "GPU", "NPU"}; +const std::vector availableDevsWithId = {"CPU", "GPU.0", "GPU.1", "NPU"}; using Params = std::tuple; using ConfigParams = std::tuple< std::vector, // Available devices retrieved from Core @@ -141,8 +141,8 @@ const std::vector testConfigsWithId = {Params{" ", " "}, Params{"CPU,,GPU", "CPU,GPU.0,GPU.1"}, Params{"CPU, ,GPU", "CPU, ,GPU.0,GPU.1"}, Params{"CPU,GPU,GPU.1", "CPU,GPU.0,GPU.1"}, - Params{"CPU,GPU,VPUX,INVALID_DEVICE", "CPU,GPU.0,GPU.1,VPUX,INVALID_DEVICE"}, - Params{"VPUX,GPU,CPU,-GPU.0", "VPUX,GPU.1,CPU"}, + Params{"CPU,GPU,NPU,INVALID_DEVICE", "CPU,GPU.0,GPU.1,NPU,INVALID_DEVICE"}, + Params{"NPU,GPU,CPU,-GPU.0", "NPU,GPU.1,CPU"}, Params{"-GPU.0,GPU,CPU", "GPU.1,CPU"}, Params{"-GPU.0,GPU", "GPU.1"}, Params{"-GPU,GPU.0", "GPU.0"}, @@ -176,10 +176,10 @@ const std::vector testConfigs = {Params{" ", " "}, Params{"CPU,GPU,GPU.0", "CPU,GPU"}, Params{"CPU,GPU,GPU.1", "CPU,GPU,GPU.1"}, Params{"CPU,GPU.1,GPU", "CPU,GPU.1,GPU"}, - Params{"CPU,VPUX", "CPU,VPUX"}, - Params{"CPU,-VPUX", "CPU"}, + Params{"CPU,NPU", "CPU,NPU"}, + Params{"CPU,-NPU", "CPU"}, Params{"CPU,-INVALID_DEVICE", "CPU"}, - Params{"CPU,GPU,VPUX", "CPU,GPU,VPUX"}}; + Params{"CPU,GPU,NPU", "CPU,GPU,NPU"}}; const std::vector testConfigsWithIdNotInteldGPU = {Params{" ", " "}, Params{"", "CPU,GPU.0"}, @@ -189,8 +189,8 @@ const std::vector testConfigsWithIdNotInteldGPU = {Params{" ", " "}, Params{"CPU,,GPU", "CPU,GPU.0,GPU.1"}, Params{"CPU, ,GPU", "CPU, ,GPU.0,GPU.1"}, Params{"CPU,GPU,GPU.1", "CPU,GPU.0,GPU.1"}, - Params{"CPU,GPU,VPUX,INVALID_DEVICE", "CPU,GPU.0,GPU.1,VPUX,INVALID_DEVICE"}, - Params{"VPUX,GPU,CPU,-GPU.0", "VPUX,GPU.1,CPU"}, + Params{"CPU,GPU,NPU,INVALID_DEVICE", "CPU,GPU.0,GPU.1,NPU,INVALID_DEVICE"}, + Params{"NPU,GPU,CPU,-GPU.0", "NPU,GPU.1,CPU"}, Params{"-GPU.0,GPU,CPU", "GPU.1,CPU"}, Params{"-GPU.0,GPU", "GPU.1"}, Params{"-GPU,GPU.0", "GPU.0"}, diff --git a/src/plugins/auto/tests/unit/key_network_priority_test.cpp b/src/plugins/auto/tests/unit/key_network_priority_test.cpp index f19fd7accdd..45aaa9272b7 100644 --- a/src/plugins/auto/tests/unit/key_network_priority_test.cpp +++ b/src/plugins/auto/tests/unit/key_network_priority_test.cpp @@ -86,7 +86,7 @@ public: IE_SET_METRIC(OPTIMIZATION_CAPABILITIES, cpuCability, {"FP32", "FP16", "INT8", "BIN"}); IE_SET_METRIC(OPTIMIZATION_CAPABILITIES, gpuCability, {"FP32", "FP16", "BATCHED_BLOB", "BIN"}); IE_SET_METRIC(OPTIMIZATION_CAPABILITIES, myriadCability, {"FP16"}); - IE_SET_METRIC(OPTIMIZATION_CAPABILITIES, vpuxCability, {"INT8"}); + IE_SET_METRIC(OPTIMIZATION_CAPABILITIES, npuCability, {"INT8"}); ON_CALL(*core, GetMetric(StrEq(CommonTestUtils::DEVICE_CPU), StrEq(METRIC_KEY(OPTIMIZATION_CAPABILITIES)), _)).WillByDefault(RETURN_MOCK_VALUE(cpuCability)); ON_CALL(*core, GetMetric(HasSubstr("GPU"), @@ -94,7 +94,7 @@ public: ON_CALL(*core, GetMetric(StrEq("MYRIAD"), StrEq(METRIC_KEY(OPTIMIZATION_CAPABILITIES)), _)).WillByDefault(RETURN_MOCK_VALUE(myriadCability)); ON_CALL(*core, GetMetric(StrEq(CommonTestUtils::DEVICE_KEEMBAY), - StrEq(METRIC_KEY(OPTIMIZATION_CAPABILITIES)), _)).WillByDefault(RETURN_MOCK_VALUE(vpuxCability)); + StrEq(METRIC_KEY(OPTIMIZATION_CAPABILITIES)), _)).WillByDefault(RETURN_MOCK_VALUE(npuCability)); ON_CALL(*core, GetMetric(HasSubstr("GPU"), StrEq(METRIC_KEY(DEVICE_ARCHITECTURE)), _)).WillByDefault(Return("GPU: vendor=0x8086 arch=0")); ON_CALL(*core, GetMetric(StrEq("GPU"), @@ -127,13 +127,13 @@ TEST_P(KeyNetworkPriorityTest, SelectDevice) { {"GPU.0", {}, 2, "01", "iGPU_01", 1}, {"GPU.1", {}, 2, "01", "dGPU_01", 2}, {"MYRIAD", {}, 2, "01", "MYRIAD_01", 3}, - {CommonTestUtils::DEVICE_KEEMBAY, {}, 2, "01", "VPUX_01", 4}}; + {CommonTestUtils::DEVICE_KEEMBAY, {}, 2, "01", "NPU_01", 4}}; } else { metaDevices = {{CommonTestUtils::DEVICE_CPU, {}, 2, "", "CPU_01", 0}, {"GPU.0", {}, 2, "01", "iGPU_01", 0}, {"GPU.1", {}, 2, "01", "dGPU_01", 0}, {"MYRIAD", {}, 2, "01", "MYRIAD_01", 0}, - {CommonTestUtils::DEVICE_KEEMBAY, {}, 2, "01", "VPUX_01", 0}}; + {CommonTestUtils::DEVICE_KEEMBAY, {}, 2, "01", "NPU_01", 0}}; } EXPECT_CALL(*plugin, SelectDevice(_, _, _)).Times(sizeOfConfigs); @@ -156,13 +156,13 @@ TEST_P(KeyNetworkPriorityTest, MultiThreadsSelectDevice) { {"GPU.0", {}, 2, "01", "iGPU_01", 1}, {"GPU.1", {}, 2, "01", "dGPU_01", 2}, {"MYRIAD", {}, 2, "01", "MYRIAD_01", 3}, - {CommonTestUtils::DEVICE_KEEMBAY, {}, 2, "01", "VPUX_01", 4}}; + {CommonTestUtils::DEVICE_KEEMBAY, {}, 2, "01", "NPU_01", 4}}; } else { metaDevices = {{CommonTestUtils::DEVICE_CPU, {}, 2, "", "CPU_01", 0}, {"GPU.0", {}, 2, "01", "iGPU_01", 0}, {"GPU.1", {}, 2, "01", "dGPU_01", 0}, {"MYRIAD", {}, 2, "01", "MYRIAD_01", 0}, - {CommonTestUtils::DEVICE_KEEMBAY, {}, 2, "01", "VPUX_01", 0}}; + {CommonTestUtils::DEVICE_KEEMBAY, {}, 2, "01", "NPU_01", 0}}; } EXPECT_CALL(*plugin, SelectDevice(_, _, _)).Times(sizeOfConfigs * 2); @@ -225,27 +225,27 @@ const std::vector testConfigs = { PriorityParams {1, "iGPU_01"}, PriorityParams {2, "CPU_01"}, PriorityParams {3, "MYRIAD_01"}}}, - ConfigParams {"INT8", false, {PriorityParams {0, "VPUX_01"}, + ConfigParams {"INT8", false, {PriorityParams {0, "NPU_01"}, PriorityParams {1, "CPU_01"}, PriorityParams {2, "CPU_01"}, PriorityParams {2, "CPU_01"}}}, - ConfigParams {"INT8", false, {PriorityParams {2, "VPUX_01"}, + ConfigParams {"INT8", false, {PriorityParams {2, "NPU_01"}, PriorityParams {3, "CPU_01"}, PriorityParams {4, "CPU_01"}, PriorityParams {5, "CPU_01"}}}, - ConfigParams {"INT8", false, {PriorityParams {2, "VPUX_01"}, - PriorityParams {0, "VPUX_01"}, + ConfigParams {"INT8", false, {PriorityParams {2, "NPU_01"}, + PriorityParams {0, "NPU_01"}, PriorityParams {2, "CPU_01"}, PriorityParams {2, "CPU_01"}}}, - ConfigParams {"INT8", false, {PriorityParams {2, "VPUX_01"}, - PriorityParams {0, "VPUX_01"}, + ConfigParams {"INT8", false, {PriorityParams {2, "NPU_01"}, + PriorityParams {0, "NPU_01"}, PriorityParams {2, "CPU_01"}, PriorityParams {3, "CPU_01"}}}, - ConfigParams {"INT8", false, {PriorityParams {0, "VPUX_01"}, + ConfigParams {"INT8", false, {PriorityParams {0, "NPU_01"}, PriorityParams {1, "CPU_01"}, PriorityParams {2, "CPU_01"}, PriorityParams {3, "CPU_01"}, - PriorityParams {0, "VPUX_01"}, + PriorityParams {0, "NPU_01"}, PriorityParams {1, "CPU_01"}, PriorityParams {2, "CPU_01"}, PriorityParams {3, "CPU_01"}}}, @@ -277,8 +277,8 @@ const std::vector testConfigs = { // {CommonTestUtils::DEVICE_GPU, {}, 2, "01", "iGPU_01", 1}, // {CommonTestUtils::DEVICE_GPU, {}, 2, "01", "dGPU_01", 2}, // {"MYRIAD", {}, 2, "01", "MYRIAD_01", 3}, - // {CommonTestUtils::DEVICE_KEEMBAY, {}, 2, "01", "VPUX_01", 4}}; - // cpu > igpu > dgpu > MYRIAD > VPUX + // {CommonTestUtils::DEVICE_KEEMBAY, {}, 2, "01", "NPU_01", 4}}; + // cpu > igpu > dgpu > MYRIAD > NPU ConfigParams {"FP32", true, {PriorityParams {0, "CPU_01"}, PriorityParams {1, "iGPU_01"}, PriorityParams {2, "dGPU_01"}, @@ -304,29 +304,29 @@ const std::vector testConfigs = { PriorityParams {2, "dGPU_01"}, PriorityParams {3, "MYRIAD_01"}}}, ConfigParams {"INT8", true, {PriorityParams {0, "CPU_01"}, - PriorityParams {1, "VPUX_01"}, - PriorityParams {2, "VPUX_01"}, - PriorityParams {2, "VPUX_01"}}}, + PriorityParams {1, "NPU_01"}, + PriorityParams {2, "NPU_01"}, + PriorityParams {2, "NPU_01"}}}, ConfigParams {"INT8", true, {PriorityParams {2, "CPU_01"}, - PriorityParams {3, "VPUX_01"}, - PriorityParams {4, "VPUX_01"}, - PriorityParams {5, "VPUX_01"}}}, + PriorityParams {3, "NPU_01"}, + PriorityParams {4, "NPU_01"}, + PriorityParams {5, "NPU_01"}}}, ConfigParams {"INT8", true, {PriorityParams {2, "CPU_01"}, PriorityParams {0, "CPU_01"}, - PriorityParams {2, "VPUX_01"}, - PriorityParams {2, "VPUX_01"}}}, + PriorityParams {2, "NPU_01"}, + PriorityParams {2, "NPU_01"}}}, ConfigParams {"INT8", true, {PriorityParams {2, "CPU_01"}, PriorityParams {0, "CPU_01"}, - PriorityParams {2, "VPUX_01"}, - PriorityParams {3, "VPUX_01"}}}, + PriorityParams {2, "NPU_01"}, + PriorityParams {3, "NPU_01"}}}, ConfigParams {"INT8", true, {PriorityParams {0, "CPU_01"}, - PriorityParams {1, "VPUX_01"}, - PriorityParams {2, "VPUX_01"}, - PriorityParams {3, "VPUX_01"}, + PriorityParams {1, "NPU_01"}, + PriorityParams {2, "NPU_01"}, + PriorityParams {3, "NPU_01"}, PriorityParams {0, "CPU_01"}, - PriorityParams {1, "VPUX_01"}, - PriorityParams {2, "VPUX_01"}, - PriorityParams {3, "VPUX_01"}}}, + PriorityParams {1, "NPU_01"}, + PriorityParams {2, "NPU_01"}, + PriorityParams {3, "NPU_01"}}}, ConfigParams {"BIN", true, {PriorityParams {0, "CPU_01"}, PriorityParams {1, "iGPU_01"}, PriorityParams {2, "dGPU_01"}, diff --git a/src/plugins/auto/tests/unit/parse_meta_device_test.cpp b/src/plugins/auto/tests/unit/parse_meta_device_test.cpp index 70d387942e1..51133de939b 100644 --- a/src/plugins/auto/tests/unit/parse_meta_device_test.cpp +++ b/src/plugins/auto/tests/unit/parse_meta_device_test.cpp @@ -39,10 +39,8 @@ using namespace MockMultiDevice; // const char cpuFullDeviceName[] = "Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz"; const char igpuFullDeviceName[] = "Intel(R) Gen9 HD Graphics (iGPU)"; const char dgpuFullDeviceName[] = "Intel(R) Iris(R) Xe MAX Graphics (dGPU)"; -// const char myriadFullDeviceName[] = "Intel Movidius Myriad X VPU"; -// const char vpuxFullDeviceName[] = ""; -const std::vector availableDevs = {"CPU", "GPU.0", "GPU.1", "VPUX"}; -const std::vector availableDevsNoID = {"CPU", "GPU", "VPUX"}; +const std::vector availableDevs = {"CPU", "GPU.0", "GPU.1", "NPU"}; +const std::vector availableDevsNoID = {"CPU", "GPU", "NPU"}; using ConfigParams = std::tuple< std::string, // Priority devices std::vector, // expect metaDevices @@ -201,62 +199,62 @@ TEST_P(ParseMetaDeviceNoIDTest, ParseMetaDevices) { // ConfigParams {devicePriority, expect metaDevices, ifThrowException} const std::vector testConfigs = { - // ConfigParams {"CPU,GPU,MYRIAD,VPUX", + // ConfigParams {"CPU,GPU,MYRIAD,NPU", // {{"CPU", {}, -1, "", "CPU_", 0}, // {"GPU.0", {}, -1, "0", std::string(igpuFullDeviceName) + "_0", 1}, // {"GPU.1", {}, -1, "1", std::string(dgpuFullDeviceName) + "_1", 1}, // {"MYRIAD.9.2-ma2480", {}, -1, "9.2-ma2480", "MYRIAD_9.2-ma2480", 2}, // {"MYRIAD.9.1-ma2480", {}, -1, "9.1-ma2480", "MYRIAD_9.1-ma2480", 2}, - // {"VPUX", {}, -1, "", "VPUX_", 3}}, false}, - // ConfigParams {"VPUX,MYRIAD,GPU,CPU", - // {{"VPUX", {}, -1, "", "VPUX_", 0}, + // {"NPU", {}, -1, "", "NPU_", 3}}, false}, + // ConfigParams {"NPU,MYRIAD,GPU,CPU", + // {{"NPU", {}, -1, "", "NPU_", 0}, // {"MYRIAD.9.2-ma2480", {}, -1, "9.2-ma2480", "MYRIAD_9.2-ma2480", 1}, // {"MYRIAD.9.1-ma2480", {}, -1, "9.1-ma2480", "MYRIAD_9.1-ma2480", 1}, // {"GPU.0", {}, -1, "0", std::string(igpuFullDeviceName) + "_0", 2}, // {"GPU.1", {}, -1, "1", std::string(dgpuFullDeviceName) + "_1", 2}, // {"CPU", {}, -1, "", "CPU_", 3}}, false}, - // ConfigParams {"CPU(1),GPU(2),MYRIAD(3),VPUX(4)", + // ConfigParams {"CPU(1),GPU(2),MYRIAD(3),NPU(4)", // {{"CPU", {}, 1, "", "CPU_", 0}, // {"GPU.0", {}, 2, "0", std::string(igpuFullDeviceName) + "_0", 1}, // {"GPU.1", {}, 2, "1", std::string(dgpuFullDeviceName) + "_1", 1}, // {"MYRIAD.9.2-ma2480", {}, 3, "9.2-ma2480", "MYRIAD_9.2-ma2480", 2}, // {"MYRIAD.9.1-ma2480", {}, 3, "9.1-ma2480", "MYRIAD_9.1-ma2480", 2}, - // {"VPUX", {}, 4, "", "VPUX_", 3}}, false}, + // {"NPU", {}, 4, "", "NPU_", 3}}, false}, // - ConfigParams {"CPU,GPU,VPUX", + ConfigParams {"CPU,GPU,NPU", {{"CPU", {}, -1, "", "CPU_", 0}, {"GPU.0", {}, -1, "", std::string(igpuFullDeviceName) + "_0", 1}, {"GPU.1", {}, -1, "", std::string(dgpuFullDeviceName) + "_1", 1}, - {"VPUX", {}, -1, "", "VPUX_", 2}}, false}, - ConfigParams {"VPUX,GPU,CPU", - {{"VPUX", {}, -1, "", "VPUX_", 0}, + {"NPU", {}, -1, "", "NPU_", 2}}, false}, + ConfigParams {"NPU,GPU,CPU", + {{"NPU", {}, -1, "", "NPU_", 0}, {"GPU.0", {}, -1, "", std::string(igpuFullDeviceName) + "_0", 1}, {"GPU.1", {}, -1, "", std::string(dgpuFullDeviceName) + "_1", 1}, {"CPU", {}, -1, "", "CPU_", 2}}, false}, - ConfigParams {"CPU(1),GPU(2),VPUX(4)", + ConfigParams {"CPU(1),GPU(2),NPU(4)", {{"CPU", {}, 1, "", "CPU_", 0}, {"GPU.0", {}, 2, "", std::string(igpuFullDeviceName) + "_0", 1}, {"GPU.1", {}, 2, "", std::string(dgpuFullDeviceName) + "_1", 1}, - {"VPUX", {}, 4, "", "VPUX_", 2}}, false}, + {"NPU", {}, 4, "", "NPU_", 2}}, false}, - ConfigParams {"CPU(-1),GPU,VPUX", {}, true}, - ConfigParams {"CPU(NA),GPU,VPUX", {}, true}, + ConfigParams {"CPU(-1),GPU,NPU", {}, true}, + ConfigParams {"CPU(NA),GPU,NPU", {}, true}, - ConfigParams {"CPU(3),GPU.1,VPUX", + ConfigParams {"CPU(3),GPU.1,NPU", {{"CPU", {}, 3, "", "CPU_", 0}, {"GPU.1", {}, -1, "", std::string(dgpuFullDeviceName) + "_1", 1}, - {"VPUX", {}, -1, "", "VPUX_", 2}}, false}, - ConfigParams {"VPUX,GPU.1,CPU(3)", - {{"VPUX", {}, -1, "", "VPUX_", 0}, + {"NPU", {}, -1, "", "NPU_", 2}}, false}, + ConfigParams {"NPU,GPU.1,CPU(3)", + {{"NPU", {}, -1, "", "NPU_", 0}, {"GPU.1", {}, -1, "", std::string(dgpuFullDeviceName) + "_1", 1}, {"CPU", {}, 3, "", "CPU_", 2}}, false} }; const std::vector testConfigsNoID = { - ConfigParams {"CPU,GPU,VPUX", + ConfigParams {"CPU,GPU,NPU", {{"CPU", {}, -1, "", "CPU_", 0}, {"GPU", {}, -1, "0", std::string(igpuFullDeviceName) + "_0", 1}, - {"VPUX", {}, -1, "", "VPUX_", 2}}, false}, + {"NPU", {}, -1, "", "NPU_", 2}}, false}, }; diff --git a/src/plugins/auto/tests/unit/select_device_test.cpp b/src/plugins/auto/tests/unit/select_device_test.cpp index 7e9ad02bab7..53008d6b101 100644 --- a/src/plugins/auto/tests/unit/select_device_test.cpp +++ b/src/plugins/auto/tests/unit/select_device_test.cpp @@ -47,10 +47,10 @@ const DeviceInformation CPU_INFO = {CommonTestUtils::DEVICE_CPU, {}, 2, "01", "C const DeviceInformation IGPU_INFO = {"GPU.0", {}, 2, "01", "iGPU_01"}; const DeviceInformation DGPU_INFO = {"GPU.1", {}, 2, "01", "dGPU_01"}; const DeviceInformation MYRIAD_INFO = {"MYRIAD", {}, 2, "01", "MYRIAD_01" }; -const DeviceInformation KEEMBAY_INFO = {CommonTestUtils::DEVICE_KEEMBAY, {}, 2, "01", "VPUX_01" }; +const DeviceInformation NPU_INFO = {CommonTestUtils::DEVICE_KEEMBAY, {}, 2, "01", "NPU_01" }; const std::vector fp32DeviceVector = {DGPU_INFO, IGPU_INFO, CPU_INFO, MYRIAD_INFO}; const std::vector fp16DeviceVector = {DGPU_INFO, IGPU_INFO, MYRIAD_INFO, CPU_INFO}; -const std::vector int8DeviceVector = {KEEMBAY_INFO, DGPU_INFO, IGPU_INFO, CPU_INFO}; +const std::vector int8DeviceVector = {NPU_INFO, DGPU_INFO, IGPU_INFO, CPU_INFO}; const std::vector binDeviceVector = {DGPU_INFO, IGPU_INFO, CPU_INFO}; const std::vector batchedblobDeviceVector = {DGPU_INFO, IGPU_INFO}; std::map> devicesMap = {{"FP32", fp32DeviceVector}, @@ -59,8 +59,8 @@ std::map> devicesMap = {{"FP32 {"BIN", binDeviceVector}, {"BATCHED_BLOB", batchedblobDeviceVector} }; -const std::vector totalDevices = {DGPU_INFO, IGPU_INFO, MYRIAD_INFO, CPU_INFO, KEEMBAY_INFO}; -const std::vector reverseTotalDevices = {KEEMBAY_INFO, CPU_INFO, MYRIAD_INFO, IGPU_INFO, DGPU_INFO}; +const std::vector totalDevices = {DGPU_INFO, IGPU_INFO, MYRIAD_INFO, CPU_INFO, NPU_INFO}; +const std::vector reverseTotalDevices = {NPU_INFO, CPU_INFO, MYRIAD_INFO, IGPU_INFO, DGPU_INFO}; const std::vector netPrecisions = {"FP32", "FP16", "INT8", "BIN", "BATCHED_BLOB"}; std::vector testConfigs; @@ -238,7 +238,7 @@ public: IE_SET_METRIC(OPTIMIZATION_CAPABILITIES, cpuCability, {"FP32", "FP16", "INT8", "BIN"}); IE_SET_METRIC(OPTIMIZATION_CAPABILITIES, gpuCability, {"FP32", "FP16", "BATCHED_BLOB", "BIN", "INT8"}); IE_SET_METRIC(OPTIMIZATION_CAPABILITIES, myriadCability, {"FP16"}); - IE_SET_METRIC(OPTIMIZATION_CAPABILITIES, vpuxCability, {"INT8"}); + IE_SET_METRIC(OPTIMIZATION_CAPABILITIES, npuCability, {"INT8"}); IE_SET_METRIC(DEVICE_ARCHITECTURE, gpuArchitecture, "GPU: vendor=0x8086 arch=0"); IE_SET_METRIC(DEVICE_TYPE, dGpuType, Metrics::DeviceType::discrete); IE_SET_METRIC(DEVICE_TYPE, iGpuType, Metrics::DeviceType::integrated); @@ -250,7 +250,7 @@ public: ON_CALL(*core, GetMetric(StrEq("MYRIAD"), StrEq(METRIC_KEY(OPTIMIZATION_CAPABILITIES)), _)).WillByDefault(RETURN_MOCK_VALUE(myriadCability)); ON_CALL(*core, GetMetric(StrEq(CommonTestUtils::DEVICE_KEEMBAY), - StrEq(METRIC_KEY(OPTIMIZATION_CAPABILITIES)), _)).WillByDefault(RETURN_MOCK_VALUE(vpuxCability)); + StrEq(METRIC_KEY(OPTIMIZATION_CAPABILITIES)), _)).WillByDefault(RETURN_MOCK_VALUE(npuCability)); ON_CALL(*core, GetMetric(HasSubstr("GPU"), StrEq(METRIC_KEY(DEVICE_ARCHITECTURE)), _)).WillByDefault(RETURN_MOCK_VALUE(gpuArchitecture)); ON_CALL(*core, GetMetric(StrEq("GPU"), diff --git a/src/tests/functional/plugin/conformance/test_runner/api_conformance_runner/include/api_conformance_helpers.hpp b/src/tests/functional/plugin/conformance/test_runner/api_conformance_runner/include/api_conformance_helpers.hpp index f3d44dcbd23..48729537bfd 100644 --- a/src/tests/functional/plugin/conformance/test_runner/api_conformance_runner/include/api_conformance_helpers.hpp +++ b/src/tests/functional/plugin/conformance/test_runner/api_conformance_runner/include/api_conformance_helpers.hpp @@ -17,7 +17,7 @@ inline const std::string get_plugin_lib_name_by_device(const std::string& device { "HETERO", "openvino_hetero_plugin" }, { "BATCH", "openvino_auto_batch_plugin" }, { "MULTI", "openvino_auto_plugin" }, - { "VPUX", "openvino_intel_vpux_plugin" }, + { "NPU", "openvino_intel_npu_plugin" }, { "CPU", "openvino_intel_cpu_plugin" }, { "GNA", "openvino_intel_gna_plugin" }, { "GPU", "openvino_intel_gpu_plugin" }, diff --git a/src/tests/ie_test_utils/common_test_utils/test_constants.cpp b/src/tests/ie_test_utils/common_test_utils/test_constants.cpp index d601e9dec65..c04e0946046 100644 --- a/src/tests/ie_test_utils/common_test_utils/test_constants.cpp +++ b/src/tests/ie_test_utils/common_test_utils/test_constants.cpp @@ -10,8 +10,8 @@ const char *DEVICE_AUTO = "AUTO"; const char *DEVICE_CPU = "CPU"; const char *DEVICE_GNA = "GNA"; const char *DEVICE_GPU = "GPU"; +const char *DEVICE_KEEMBAY = "NPU"; const char *DEVICE_BATCH = "BATCH"; -const char *DEVICE_KEEMBAY = "VPUX"; const char *DEVICE_MULTI = "MULTI"; const char *DEVICE_TEMPLATE = "TEMPLATE"; const char *DEVICE_HETERO = "HETERO"; diff --git a/src/tests/ie_test_utils/common_test_utils/test_constants.hpp b/src/tests/ie_test_utils/common_test_utils/test_constants.hpp index 65f5cc0fe11..1ecbc41f563 100644 --- a/src/tests/ie_test_utils/common_test_utils/test_constants.hpp +++ b/src/tests/ie_test_utils/common_test_utils/test_constants.hpp @@ -10,8 +10,8 @@ extern const char* DEVICE_AUTO; extern const char* DEVICE_CPU; extern const char* DEVICE_GNA; extern const char* DEVICE_GPU; -extern const char* DEVICE_BATCH; extern const char* DEVICE_KEEMBAY; +extern const char* DEVICE_BATCH; extern const char* DEVICE_MULTI; extern const char* DEVICE_TEMPLATE; extern const char* DEVICE_HETERO; diff --git a/tests/time_tests/.automation/desktop_test_config.yml b/tests/time_tests/.automation/desktop_test_config.yml index 30149dd929d..a21ebe0d201 100644 --- a/tests/time_tests/.automation/desktop_test_config.yml +++ b/tests/time_tests/.automation/desktop_test_config.yml @@ -1,448 +1,448 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/resnet-50-pytorch/onnx/FP16/resnet-50-pytorch.xml + path: ${NPU_MODELS_PKG}/resnet-50-pytorch/onnx/FP16/resnet-50-pytorch.xml name: resnet-50-pytorch precision: FP16 framework: onnx - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/resnet-50-pytorch/onnx/FP16/resnet-50-pytorch.xml + path: ${NPU_MODELS_PKG}/resnet-50-pytorch/onnx/FP16/resnet-50-pytorch.xml name: resnet-50-pytorch precision: FP16 framework: onnx - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/resnet-50-pytorch/onnx/FP16-INT8/resnet-50-pytorch.xml + path: ${NPU_MODELS_PKG}/resnet-50-pytorch/onnx/FP16-INT8/resnet-50-pytorch.xml name: resnet-50-pytorch precision: FP16-INT8 framework: onnx - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/resnet-50-pytorch/onnx/FP16-INT8/resnet-50-pytorch.xml + path: ${NPU_MODELS_PKG}/resnet-50-pytorch/onnx/FP16-INT8/resnet-50-pytorch.xml name: resnet-50-pytorch precision: FP16-INT8 framework: onnx - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/mobilenet-v2/caffe/FP16/mobilenet-v2.xml + path: ${NPU_MODELS_PKG}/mobilenet-v2/caffe/FP16/mobilenet-v2.xml name: mobilenet-v2 precision: FP16 framework: caffe - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/mobilenet-v2/caffe/FP16/mobilenet-v2.xml + path: ${NPU_MODELS_PKG}/mobilenet-v2/caffe/FP16/mobilenet-v2.xml name: mobilenet-v2 precision: FP16 framework: caffe - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/mobilenet-v2/caffe/FP16-INT8/mobilenet-v2.xml + path: ${NPU_MODELS_PKG}/mobilenet-v2/caffe/FP16-INT8/mobilenet-v2.xml name: mobilenet-v2 precision: FP16-INT8 framework: caffe - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/mobilenet-v2/caffe/FP16-INT8/mobilenet-v2.xml + path: ${NPU_MODELS_PKG}/mobilenet-v2/caffe/FP16-INT8/mobilenet-v2.xml name: mobilenet-v2 precision: FP16-INT8 framework: caffe - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16/faster-rcnn-resnet101-coco-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16/faster-rcnn-resnet101-coco-sparse-60-0001.xml name: faster-rcnn-resnet101-coco-sparse-60-0001 precision: FP16 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16/faster-rcnn-resnet101-coco-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16/faster-rcnn-resnet101-coco-sparse-60-0001.xml name: faster-rcnn-resnet101-coco-sparse-60-0001 precision: FP16 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16-INT8/faster-rcnn-resnet101-coco-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16-INT8/faster-rcnn-resnet101-coco-sparse-60-0001.xml name: faster-rcnn-resnet101-coco-sparse-60-0001 precision: FP16-INT8 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16-INT8/faster-rcnn-resnet101-coco-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16-INT8/faster-rcnn-resnet101-coco-sparse-60-0001.xml name: faster-rcnn-resnet101-coco-sparse-60-0001 precision: FP16-INT8 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v1/tf/FP16/googlenet-v1.xml + path: ${NPU_MODELS_PKG}/googlenet-v1/tf/FP16/googlenet-v1.xml name: googlenet-v1 precision: FP16 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v1/tf/FP16/googlenet-v1.xml + path: ${NPU_MODELS_PKG}/googlenet-v1/tf/FP16/googlenet-v1.xml name: googlenet-v1 precision: FP16 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v1/tf/FP16-INT8/googlenet-v1.xml + path: ${NPU_MODELS_PKG}/googlenet-v1/tf/FP16-INT8/googlenet-v1.xml name: googlenet-v1 precision: FP16-INT8 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v1/tf/FP16-INT8/googlenet-v1.xml + path: ${NPU_MODELS_PKG}/googlenet-v1/tf/FP16-INT8/googlenet-v1.xml name: googlenet-v1 precision: FP16-INT8 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v3/tf/FP16/googlenet-v3.xml + path: ${NPU_MODELS_PKG}/googlenet-v3/tf/FP16/googlenet-v3.xml name: googlenet-v3 precision: FP16 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v3/tf/FP16/googlenet-v3.xml + path: ${NPU_MODELS_PKG}/googlenet-v3/tf/FP16/googlenet-v3.xml name: googlenet-v3 precision: FP16 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v3/tf/FP16-INT8/googlenet-v3.xml + path: ${NPU_MODELS_PKG}/googlenet-v3/tf/FP16-INT8/googlenet-v3.xml name: googlenet-v3 precision: FP16-INT8 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v3/tf/FP16-INT8/googlenet-v3.xml + path: ${NPU_MODELS_PKG}/googlenet-v3/tf/FP16-INT8/googlenet-v3.xml name: googlenet-v3 precision: FP16-INT8 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/ssd512/caffe/FP16/ssd512.xml + path: ${NPU_MODELS_PKG}/ssd512/caffe/FP16/ssd512.xml name: ssd512 precision: FP16 framework: caffe - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/ssd512/caffe/FP16/ssd512.xml + path: ${NPU_MODELS_PKG}/ssd512/caffe/FP16/ssd512.xml name: ssd512 precision: FP16 framework: caffe - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/ssd512/caffe/FP16-INT8/ssd512.xml + path: ${NPU_MODELS_PKG}/ssd512/caffe/FP16-INT8/ssd512.xml name: ssd512 precision: FP16-INT8 framework: caffe - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/ssd512/caffe/FP16-INT8/ssd512.xml + path: ${NPU_MODELS_PKG}/ssd512/caffe/FP16-INT8/ssd512.xml name: ssd512 precision: FP16-INT8 framework: caffe - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16/yolo-v2-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16/yolo-v2-ava-0001.xml name: yolo-v2-ava-0001 precision: FP16 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16/yolo-v2-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16/yolo-v2-ava-0001.xml name: yolo-v2-ava-0001 precision: FP16 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16-INT8/yolo-v2-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16-INT8/yolo-v2-ava-0001.xml name: yolo-v2-ava-0001 precision: FP16-INT8 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16-INT8/yolo-v2-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16-INT8/yolo-v2-ava-0001.xml name: yolo-v2-ava-0001 precision: FP16-INT8 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16/yolo-v2-ava-sparse-35-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16/yolo-v2-ava-sparse-35-0001.xml name: yolo-v2-ava-sparse-35-0001 precision: FP16 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16/yolo-v2-ava-sparse-35-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16/yolo-v2-ava-sparse-35-0001.xml name: yolo-v2-ava-sparse-35-0001 precision: FP16 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16-INT8/yolo-v2-ava-sparse-35-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16-INT8/yolo-v2-ava-sparse-35-0001.xml name: yolo-v2-ava-sparse-35-0001 precision: FP16-INT8 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16-INT8/yolo-v2-ava-sparse-35-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16-INT8/yolo-v2-ava-sparse-35-0001.xml name: yolo-v2-ava-sparse-35-0001 precision: FP16-INT8 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16/yolo-v2-ava-sparse-70-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16/yolo-v2-ava-sparse-70-0001.xml name: yolo-v2-ava-sparse-70-0001 precision: FP16 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16/yolo-v2-ava-sparse-70-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16/yolo-v2-ava-sparse-70-0001.xml name: yolo-v2-ava-sparse-70-0001 precision: FP16 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16-INT8/yolo-v2-ava-sparse-70-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16-INT8/yolo-v2-ava-sparse-70-0001.xml name: yolo-v2-ava-sparse-70-0001 precision: FP16-INT8 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16-INT8/yolo-v2-ava-sparse-70-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16-INT8/yolo-v2-ava-sparse-70-0001.xml name: yolo-v2-ava-sparse-70-0001 precision: FP16-INT8 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16/yolo-v2-tiny-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16/yolo-v2-tiny-ava-0001.xml name: yolo-v2-tiny-ava-0001 precision: FP16 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16/yolo-v2-tiny-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16/yolo-v2-tiny-ava-0001.xml name: yolo-v2-tiny-ava-0001 precision: FP16 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16-INT8/yolo-v2-tiny-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16-INT8/yolo-v2-tiny-ava-0001.xml name: yolo-v2-tiny-ava-0001 precision: FP16-INT8 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16-INT8/yolo-v2-tiny-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16-INT8/yolo-v2-tiny-ava-0001.xml name: yolo-v2-tiny-ava-0001 precision: FP16-INT8 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16/yolo-v2-tiny-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16/yolo-v2-tiny-ava-sparse-30-0001.xml name: yolo-v2-tiny-ava-sparse-30-0001 precision: FP16 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16/yolo-v2-tiny-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16/yolo-v2-tiny-ava-sparse-30-0001.xml name: yolo-v2-tiny-ava-sparse-30-0001 precision: FP16 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-30-0001.xml name: yolo-v2-tiny-ava-sparse-30-0001 precision: FP16-INT8 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-30-0001.xml name: yolo-v2-tiny-ava-sparse-30-0001 precision: FP16-INT8 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16/yolo-v2-tiny-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16/yolo-v2-tiny-ava-sparse-60-0001.xml name: yolo-v2-tiny-ava-sparse-60-0001 precision: FP16 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16/yolo-v2-tiny-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16/yolo-v2-tiny-ava-sparse-60-0001.xml name: yolo-v2-tiny-ava-sparse-60-0001 precision: FP16 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-60-0001.xml name: yolo-v2-tiny-ava-sparse-60-0001 precision: FP16-INT8 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-60-0001.xml name: yolo-v2-tiny-ava-sparse-60-0001 precision: FP16-INT8 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/squeezenet1.1/caffe/FP16/squeezenet1.1.xml + path: ${NPU_MODELS_PKG}/squeezenet1.1/caffe/FP16/squeezenet1.1.xml name: squeezenet1.1 precision: FP16 framework: caffe - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/squeezenet1.1/caffe/FP16/squeezenet1.1.xml + path: ${NPU_MODELS_PKG}/squeezenet1.1/caffe/FP16/squeezenet1.1.xml name: squeezenet1.1 precision: FP16 framework: caffe - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/squeezenet1.1/caffe/FP16-INT8/squeezenet1.1.xml + path: ${NPU_MODELS_PKG}/squeezenet1.1/caffe/FP16-INT8/squeezenet1.1.xml name: squeezenet1.1 precision: FP16-INT8 framework: caffe - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/squeezenet1.1/caffe/FP16-INT8/squeezenet1.1.xml + path: ${NPU_MODELS_PKG}/squeezenet1.1/caffe/FP16-INT8/squeezenet1.1.xml name: squeezenet1.1 precision: FP16-INT8 framework: caffe - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16/icnet-camvid-ava-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16/icnet-camvid-ava-0001.xml name: icnet-camvid-ava-0001 precision: FP16 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16/icnet-camvid-ava-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16/icnet-camvid-ava-0001.xml name: icnet-camvid-ava-0001 precision: FP16 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16-INT8/icnet-camvid-ava-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16-INT8/icnet-camvid-ava-0001.xml name: icnet-camvid-ava-0001 precision: FP16-INT8 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16-INT8/icnet-camvid-ava-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16-INT8/icnet-camvid-ava-0001.xml name: icnet-camvid-ava-0001 precision: FP16-INT8 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16/icnet-camvid-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16/icnet-camvid-ava-sparse-30-0001.xml name: icnet-camvid-ava-sparse-30-0001 precision: FP16 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16/icnet-camvid-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16/icnet-camvid-ava-sparse-30-0001.xml name: icnet-camvid-ava-sparse-30-0001 precision: FP16 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-30-0001.xml name: icnet-camvid-ava-sparse-30-0001 precision: FP16-INT8 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-30-0001.xml name: icnet-camvid-ava-sparse-30-0001 precision: FP16-INT8 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16/icnet-camvid-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16/icnet-camvid-ava-sparse-60-0001.xml name: icnet-camvid-ava-sparse-60-0001 precision: FP16 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16/icnet-camvid-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16/icnet-camvid-ava-sparse-60-0001.xml name: icnet-camvid-ava-sparse-60-0001 precision: FP16 framework: tf - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-60-0001.xml name: icnet-camvid-ava-sparse-60-0001 precision: FP16-INT8 framework: tf - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-60-0001.xml name: icnet-camvid-ava-sparse-60-0001 precision: FP16-INT8 framework: tf \ No newline at end of file diff --git a/tests/time_tests/.automation/desktop_test_config_cache.yml b/tests/time_tests/.automation/desktop_test_config_cache.yml index 94a2c8bedc9..a24be941289 100644 --- a/tests/time_tests/.automation/desktop_test_config_cache.yml +++ b/tests/time_tests/.automation/desktop_test_config_cache.yml @@ -1,7 +1,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/resnet-50-pytorch/onnx/FP16/resnet-50-pytorch.xml + path: ${NPU_MODELS_PKG}/resnet-50-pytorch/onnx/FP16/resnet-50-pytorch.xml name: resnet-50-pytorch precision: FP16 framework: onnx @@ -9,7 +9,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/resnet-50-pytorch/onnx/FP16/resnet-50-pytorch.xml + path: ${NPU_MODELS_PKG}/resnet-50-pytorch/onnx/FP16/resnet-50-pytorch.xml name: resnet-50-pytorch precision: FP16 framework: onnx @@ -17,7 +17,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/resnet-50-pytorch/onnx/FP16-INT8/resnet-50-pytorch.xml + path: ${NPU_MODELS_PKG}/resnet-50-pytorch/onnx/FP16-INT8/resnet-50-pytorch.xml name: resnet-50-pytorch precision: FP16-INT8 framework: onnx @@ -25,7 +25,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/resnet-50-pytorch/onnx/FP16-INT8/resnet-50-pytorch.xml + path: ${NPU_MODELS_PKG}/resnet-50-pytorch/onnx/FP16-INT8/resnet-50-pytorch.xml name: resnet-50-pytorch precision: FP16-INT8 framework: onnx @@ -33,7 +33,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/mobilenet-v2/caffe/FP16/mobilenet-v2.xml + path: ${NPU_MODELS_PKG}/mobilenet-v2/caffe/FP16/mobilenet-v2.xml name: mobilenet-v2 precision: FP16 framework: caffe @@ -41,7 +41,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/mobilenet-v2/caffe/FP16/mobilenet-v2.xml + path: ${NPU_MODELS_PKG}/mobilenet-v2/caffe/FP16/mobilenet-v2.xml name: mobilenet-v2 precision: FP16 framework: caffe @@ -49,7 +49,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/mobilenet-v2/caffe/FP16-INT8/mobilenet-v2.xml + path: ${NPU_MODELS_PKG}/mobilenet-v2/caffe/FP16-INT8/mobilenet-v2.xml name: mobilenet-v2 precision: FP16-INT8 framework: caffe @@ -57,7 +57,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/mobilenet-v2/caffe/FP16-INT8/mobilenet-v2.xml + path: ${NPU_MODELS_PKG}/mobilenet-v2/caffe/FP16-INT8/mobilenet-v2.xml name: mobilenet-v2 precision: FP16-INT8 framework: caffe @@ -65,7 +65,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16/faster-rcnn-resnet101-coco-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16/faster-rcnn-resnet101-coco-sparse-60-0001.xml name: faster-rcnn-resnet101-coco-sparse-60-0001 precision: FP16 framework: tf @@ -73,7 +73,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16/faster-rcnn-resnet101-coco-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16/faster-rcnn-resnet101-coco-sparse-60-0001.xml name: faster-rcnn-resnet101-coco-sparse-60-0001 precision: FP16 framework: tf @@ -81,7 +81,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16-INT8/faster-rcnn-resnet101-coco-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16-INT8/faster-rcnn-resnet101-coco-sparse-60-0001.xml name: faster-rcnn-resnet101-coco-sparse-60-0001 precision: FP16-INT8 framework: tf @@ -89,7 +89,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16-INT8/faster-rcnn-resnet101-coco-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/faster-rcnn-resnet101-coco-sparse-60-0001/tf/FP16-INT8/faster-rcnn-resnet101-coco-sparse-60-0001.xml name: faster-rcnn-resnet101-coco-sparse-60-0001 precision: FP16-INT8 framework: tf @@ -97,7 +97,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v1/tf/FP16/googlenet-v1.xml + path: ${NPU_MODELS_PKG}/googlenet-v1/tf/FP16/googlenet-v1.xml name: googlenet-v1 precision: FP16 framework: tf @@ -105,7 +105,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v1/tf/FP16/googlenet-v1.xml + path: ${NPU_MODELS_PKG}/googlenet-v1/tf/FP16/googlenet-v1.xml name: googlenet-v1 precision: FP16 framework: tf @@ -113,7 +113,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v1/tf/FP16-INT8/googlenet-v1.xml + path: ${NPU_MODELS_PKG}/googlenet-v1/tf/FP16-INT8/googlenet-v1.xml name: googlenet-v1 precision: FP16-INT8 framework: tf @@ -121,7 +121,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v1/tf/FP16-INT8/googlenet-v1.xml + path: ${NPU_MODELS_PKG}/googlenet-v1/tf/FP16-INT8/googlenet-v1.xml name: googlenet-v1 precision: FP16-INT8 framework: tf @@ -129,7 +129,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v3/tf/FP16/googlenet-v3.xml + path: ${NPU_MODELS_PKG}/googlenet-v3/tf/FP16/googlenet-v3.xml name: googlenet-v3 precision: FP16 framework: tf @@ -137,7 +137,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v3/tf/FP16/googlenet-v3.xml + path: ${NPU_MODELS_PKG}/googlenet-v3/tf/FP16/googlenet-v3.xml name: googlenet-v3 precision: FP16 framework: tf @@ -145,7 +145,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v3/tf/FP16-INT8/googlenet-v3.xml + path: ${NPU_MODELS_PKG}/googlenet-v3/tf/FP16-INT8/googlenet-v3.xml name: googlenet-v3 precision: FP16-INT8 framework: tf @@ -153,7 +153,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/googlenet-v3/tf/FP16-INT8/googlenet-v3.xml + path: ${NPU_MODELS_PKG}/googlenet-v3/tf/FP16-INT8/googlenet-v3.xml name: googlenet-v3 precision: FP16-INT8 framework: tf @@ -161,7 +161,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/ssd512/caffe/FP16/ssd512.xml + path: ${NPU_MODELS_PKG}/ssd512/caffe/FP16/ssd512.xml name: ssd512 precision: FP16 framework: caffe @@ -169,7 +169,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/ssd512/caffe/FP16/ssd512.xml + path: ${NPU_MODELS_PKG}/ssd512/caffe/FP16/ssd512.xml name: ssd512 precision: FP16 framework: caffe @@ -177,7 +177,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/ssd512/caffe/FP16-INT8/ssd512.xml + path: ${NPU_MODELS_PKG}/ssd512/caffe/FP16-INT8/ssd512.xml name: ssd512 precision: FP16-INT8 framework: caffe @@ -185,7 +185,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/ssd512/caffe/FP16-INT8/ssd512.xml + path: ${NPU_MODELS_PKG}/ssd512/caffe/FP16-INT8/ssd512.xml name: ssd512 precision: FP16-INT8 framework: caffe @@ -193,7 +193,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16/yolo-v2-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16/yolo-v2-ava-0001.xml name: yolo-v2-ava-0001 precision: FP16 framework: tf @@ -201,7 +201,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16/yolo-v2-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16/yolo-v2-ava-0001.xml name: yolo-v2-ava-0001 precision: FP16 framework: tf @@ -209,7 +209,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16-INT8/yolo-v2-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16-INT8/yolo-v2-ava-0001.xml name: yolo-v2-ava-0001 precision: FP16-INT8 framework: tf @@ -217,7 +217,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16-INT8/yolo-v2-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-0001/tf/FP16-INT8/yolo-v2-ava-0001.xml name: yolo-v2-ava-0001 precision: FP16-INT8 framework: tf @@ -225,7 +225,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16/yolo-v2-ava-sparse-35-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16/yolo-v2-ava-sparse-35-0001.xml name: yolo-v2-ava-sparse-35-0001 precision: FP16 framework: tf @@ -233,7 +233,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16/yolo-v2-ava-sparse-35-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16/yolo-v2-ava-sparse-35-0001.xml name: yolo-v2-ava-sparse-35-0001 precision: FP16 framework: tf @@ -241,7 +241,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16-INT8/yolo-v2-ava-sparse-35-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16-INT8/yolo-v2-ava-sparse-35-0001.xml name: yolo-v2-ava-sparse-35-0001 precision: FP16-INT8 framework: tf @@ -249,7 +249,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16-INT8/yolo-v2-ava-sparse-35-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-35-0001/tf/FP16-INT8/yolo-v2-ava-sparse-35-0001.xml name: yolo-v2-ava-sparse-35-0001 precision: FP16-INT8 framework: tf @@ -257,7 +257,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16/yolo-v2-ava-sparse-70-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16/yolo-v2-ava-sparse-70-0001.xml name: yolo-v2-ava-sparse-70-0001 precision: FP16 framework: tf @@ -265,7 +265,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16/yolo-v2-ava-sparse-70-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16/yolo-v2-ava-sparse-70-0001.xml name: yolo-v2-ava-sparse-70-0001 precision: FP16 framework: tf @@ -273,7 +273,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16-INT8/yolo-v2-ava-sparse-70-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16-INT8/yolo-v2-ava-sparse-70-0001.xml name: yolo-v2-ava-sparse-70-0001 precision: FP16-INT8 framework: tf @@ -281,7 +281,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16-INT8/yolo-v2-ava-sparse-70-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-ava-sparse-70-0001/tf/FP16-INT8/yolo-v2-ava-sparse-70-0001.xml name: yolo-v2-ava-sparse-70-0001 precision: FP16-INT8 framework: tf @@ -289,7 +289,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16/yolo-v2-tiny-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16/yolo-v2-tiny-ava-0001.xml name: yolo-v2-tiny-ava-0001 precision: FP16 framework: tf @@ -297,7 +297,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16/yolo-v2-tiny-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16/yolo-v2-tiny-ava-0001.xml name: yolo-v2-tiny-ava-0001 precision: FP16 framework: tf @@ -305,7 +305,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16-INT8/yolo-v2-tiny-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16-INT8/yolo-v2-tiny-ava-0001.xml name: yolo-v2-tiny-ava-0001 precision: FP16-INT8 framework: tf @@ -313,7 +313,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16-INT8/yolo-v2-tiny-ava-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-0001/tf/FP16-INT8/yolo-v2-tiny-ava-0001.xml name: yolo-v2-tiny-ava-0001 precision: FP16-INT8 framework: tf @@ -321,7 +321,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16/yolo-v2-tiny-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16/yolo-v2-tiny-ava-sparse-30-0001.xml name: yolo-v2-tiny-ava-sparse-30-0001 precision: FP16 framework: tf @@ -329,7 +329,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16/yolo-v2-tiny-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16/yolo-v2-tiny-ava-sparse-30-0001.xml name: yolo-v2-tiny-ava-sparse-30-0001 precision: FP16 framework: tf @@ -337,7 +337,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-30-0001.xml name: yolo-v2-tiny-ava-sparse-30-0001 precision: FP16-INT8 framework: tf @@ -345,7 +345,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-30-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-30-0001.xml name: yolo-v2-tiny-ava-sparse-30-0001 precision: FP16-INT8 framework: tf @@ -353,7 +353,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16/yolo-v2-tiny-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16/yolo-v2-tiny-ava-sparse-60-0001.xml name: yolo-v2-tiny-ava-sparse-60-0001 precision: FP16 framework: tf @@ -361,7 +361,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16/yolo-v2-tiny-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16/yolo-v2-tiny-ava-sparse-60-0001.xml name: yolo-v2-tiny-ava-sparse-60-0001 precision: FP16 framework: tf @@ -369,7 +369,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-60-0001.xml name: yolo-v2-tiny-ava-sparse-60-0001 precision: FP16-INT8 framework: tf @@ -377,7 +377,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/yolo-v2-tiny-ava-sparse-60-0001/tf/FP16-INT8/yolo-v2-tiny-ava-sparse-60-0001.xml name: yolo-v2-tiny-ava-sparse-60-0001 precision: FP16-INT8 framework: tf @@ -385,7 +385,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/squeezenet1.1/caffe/FP16/squeezenet1.1.xml + path: ${NPU_MODELS_PKG}/squeezenet1.1/caffe/FP16/squeezenet1.1.xml name: squeezenet1.1 precision: FP16 framework: caffe @@ -393,7 +393,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/squeezenet1.1/caffe/FP16/squeezenet1.1.xml + path: ${NPU_MODELS_PKG}/squeezenet1.1/caffe/FP16/squeezenet1.1.xml name: squeezenet1.1 precision: FP16 framework: caffe @@ -401,7 +401,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/squeezenet1.1/caffe/FP16-INT8/squeezenet1.1.xml + path: ${NPU_MODELS_PKG}/squeezenet1.1/caffe/FP16-INT8/squeezenet1.1.xml name: squeezenet1.1 precision: FP16-INT8 framework: caffe @@ -409,7 +409,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/squeezenet1.1/caffe/FP16-INT8/squeezenet1.1.xml + path: ${NPU_MODELS_PKG}/squeezenet1.1/caffe/FP16-INT8/squeezenet1.1.xml name: squeezenet1.1 precision: FP16-INT8 framework: caffe @@ -417,7 +417,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16/icnet-camvid-ava-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16/icnet-camvid-ava-0001.xml name: icnet-camvid-ava-0001 precision: FP16 framework: tf @@ -425,7 +425,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16/icnet-camvid-ava-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16/icnet-camvid-ava-0001.xml name: icnet-camvid-ava-0001 precision: FP16 framework: tf @@ -433,7 +433,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16-INT8/icnet-camvid-ava-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16-INT8/icnet-camvid-ava-0001.xml name: icnet-camvid-ava-0001 precision: FP16-INT8 framework: tf @@ -441,7 +441,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16-INT8/icnet-camvid-ava-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-0001/tf/FP16-INT8/icnet-camvid-ava-0001.xml name: icnet-camvid-ava-0001 precision: FP16-INT8 framework: tf @@ -449,7 +449,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16/icnet-camvid-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16/icnet-camvid-ava-sparse-30-0001.xml name: icnet-camvid-ava-sparse-30-0001 precision: FP16 framework: tf @@ -457,7 +457,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16/icnet-camvid-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16/icnet-camvid-ava-sparse-30-0001.xml name: icnet-camvid-ava-sparse-30-0001 precision: FP16 framework: tf @@ -465,7 +465,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-30-0001.xml name: icnet-camvid-ava-sparse-30-0001 precision: FP16-INT8 framework: tf @@ -473,7 +473,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-30-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-30-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-30-0001.xml name: icnet-camvid-ava-sparse-30-0001 precision: FP16-INT8 framework: tf @@ -481,7 +481,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16/icnet-camvid-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16/icnet-camvid-ava-sparse-60-0001.xml name: icnet-camvid-ava-sparse-60-0001 precision: FP16 framework: tf @@ -489,7 +489,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16/icnet-camvid-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16/icnet-camvid-ava-sparse-60-0001.xml name: icnet-camvid-ava-sparse-60-0001 precision: FP16 framework: tf @@ -497,7 +497,7 @@ - device: name: CPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-60-0001.xml name: icnet-camvid-ava-sparse-60-0001 precision: FP16-INT8 framework: tf @@ -505,7 +505,7 @@ - device: name: GPU model: - path: ${VPUX_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-60-0001.xml + path: ${NPU_MODELS_PKG}/icnet-camvid-ava-sparse-60-0001/tf/FP16-INT8/icnet-camvid-ava-sparse-60-0001.xml name: icnet-camvid-ava-sparse-60-0001 precision: FP16-INT8 framework: tf diff --git a/tests/time_tests/test_runner/test_timetest.py b/tests/time_tests/test_runner/test_timetest.py index 28acb628545..f7d7600b281 100644 --- a/tests/time_tests/test_runner/test_timetest.py +++ b/tests/time_tests/test_runner/test_timetest.py @@ -43,7 +43,7 @@ def test_timetest(instance, executable, niter, cl_cache_dir, model_cache, model_ :param niter: number of times to run executable :param cl_cache_dir: directory to store OpenCL cache :param cpu_cache: flag to enable model CPU cache - :param vpu_compiler: flag to change VPUX compiler type + :param npu_compiler: flag to change NPU compiler type :param perf_hint: performance hint (optimize device for latency or throughput settings) :param model_cache_dir: directory to store IE model cache :param test_info: custom `test_info` field of built-in `request` pytest fixture diff --git a/thirdparty/CMakeLists.txt b/thirdparty/CMakeLists.txt index fdf25376ad8..a917a6b78b0 100644 --- a/thirdparty/CMakeLists.txt +++ b/thirdparty/CMakeLists.txt @@ -600,7 +600,7 @@ endif() # if(ENABLE_SAMPLES) - # Note: VPUX requires 3.9.0 version, because it contains 'nlohmann::ordered_json' + # Note: NPU requires 3.9.0 version, because it contains 'nlohmann::ordered_json' find_package(nlohmann_json 3.9.0 QUIET) if(nlohmann_json_FOUND) # conan creates imported target nlohmann_json::nlohmann_json @@ -610,7 +610,7 @@ if(ENABLE_SAMPLES) else() add_subdirectory(json) - # this is required only because of VPUX plugin reused this + # this is required only because of NPU plugin reused this openvino_developer_export_targets(COMPONENT openvino_common TARGETS nlohmann_json) # for nlohmann library versions older than v3.0.0 diff --git a/tools/benchmark_tool/openvino/tools/benchmark/utils/constants.py b/tools/benchmark_tool/openvino/tools/benchmark/utils/constants.py index cafc3ec0911..1fb45e1f4a2 100644 --- a/tools/benchmark_tool/openvino/tools/benchmark/utils/constants.py +++ b/tools/benchmark_tool/openvino/tools/benchmark/utils/constants.py @@ -1,7 +1,7 @@ # Copyright (C) 2018-2023 Intel Corporation # SPDX-License-Identifier: Apache-2.0 -VPUX_DEVICE_NAME = 'VPUX' +NPU_DEVICE_NAME = 'NPU' CPU_DEVICE_NAME = 'CPU' GPU_DEVICE_NAME = 'GPU' HETERO_DEVICE_NAME = 'HETERO' @@ -22,7 +22,7 @@ BINARY_EXTENSIONS = ['.bin'] DEVICE_DURATION_IN_SECS = { CPU_DEVICE_NAME: 60, GPU_DEVICE_NAME: 60, - VPUX_DEVICE_NAME: 60, + NPU_DEVICE_NAME: 60, GNA_DEVICE_NAME: 60, UNKNOWN_DEVICE_TYPE: 120 } diff --git a/tools/compile_tool/main.cpp b/tools/compile_tool/main.cpp index d30609de6bb..afdcda88848 100644 --- a/tools/compile_tool/main.cpp +++ b/tools/compile_tool/main.cpp @@ -353,9 +353,9 @@ bool isFP32(const ov::element::Type& type) { static void setDefaultIO(ov::preprocess::PrePostProcessor& preprocessor, const std::vector>& inputs, const std::vector>& outputs) { - const bool isVPUX = FLAGS_d.find("VPUX") != std::string::npos; + const bool isNPU = FLAGS_d.find("NPU") != std::string::npos; - if (isVPUX) { + if (isNPU) { for (size_t i = 0; i < inputs.size(); i++) { preprocessor.input(i).tensor().set_element_type(ov::element::u8); } @@ -622,9 +622,9 @@ bool isFloat(InferenceEngine::Precision precision) { } static void setDefaultIO(InferenceEngine::CNNNetwork& network) { - const bool isVPUX = FLAGS_d.find("VPUX") != std::string::npos; + const bool isNPU = FLAGS_d.find("NPU") != std::string::npos; - if (isVPUX) { + if (isNPU) { const InferenceEngine::Precision u8 = InferenceEngine::Precision::U8; const InferenceEngine::Precision fp32 = InferenceEngine::Precision::FP32; diff --git a/tools/legacy/benchmark_app/utils.cpp b/tools/legacy/benchmark_app/utils.cpp index e1cd0622dd6..b109bab288b 100644 --- a/tools/legacy/benchmark_app/utils.cpp +++ b/tools/legacy/benchmark_app/utils.cpp @@ -54,7 +54,7 @@ size_t InputInfo::depth() const { } // namespace benchmark_app uint32_t deviceDefaultDeviceDurationInSeconds(const std::string& device) { - static const std::map deviceDefaultDurationInSeconds {{"CPU", 60}, {"GPU", 60}, {"VPUX", 60}, + static const std::map deviceDefaultDurationInSeconds {{"CPU", 60}, {"GPU", 60}, {"NPU", 60}, {"UNKNOWN", 120}}; uint32_t duration = 0; for (const auto& deviceDurationInSeconds : deviceDefaultDurationInSeconds) { diff --git a/tools/pot/README_dev.md b/tools/pot/README_dev.md index 785e409edd4..d524ec5bb59 100644 --- a/tools/pot/README_dev.md +++ b/tools/pot/README_dev.md @@ -13,7 +13,7 @@ Post-Training Optimization Tool includes standalone command-line tool and Python * Per-channel quantization for Convolutional and Fully-Connected layers. * Multiple domains: Computer Vision, Recommendation Systems. * Ability to implement custom calibration pipeline via supported [API](openvino/tools/pot/api/README.md). -* Compression for different HW targets such as CPU, GPU, VPU. +* Compression for different HW targets such as CPU, GPU, NPU. * Post-training sparsity. ## Usage diff --git a/tools/pot/docs/BestPractices.md b/tools/pot/docs/BestPractices.md index ab15576a06d..bee4d8fbcad 100644 --- a/tools/pot/docs/BestPractices.md +++ b/tools/pot/docs/BestPractices.md @@ -14,7 +14,7 @@ the fastest and easiest way to get a quantized model. It requires only some unan .. note:: - POT uses inference on the CPU during model optimization. It means that ability to infer the original floating-point model is essential for model optimization. In case of the 8-bit quantization, it is recommended to run POT on the same CPU architecture when optimizing for CPU or VNNI-based CPU when quantizing for a non-CPU device, such as GPU, VPU, or GNA. It should help to avoid the impact of the :doc:`saturation issue ` that occurs on AVX and SSE-based CPU devices. + POT uses inference on the CPU during model optimization. It means that ability to infer the original floating-point model is essential for model optimization. In case of the 8-bit quantization, it is recommended to run POT on the same CPU architecture when optimizing for CPU or VNNI-based CPU when quantizing for a non-CPU device, such as GPU, NPU, or GNA. It should help to avoid the impact of the :doc:`saturation issue ` that occurs on AVX and SSE-based CPU devices. Improving accuracy after the Default Quantization @@ -32,7 +32,7 @@ Parameters of the Default Quantization algorithm with basic settings are present # the quantization scheme. For the CPU: # performance - symmetric quantization of weights and activations. # mixed - symmetric weights and asymmetric activations. - # accuracy - the same as "mixed" for CPU, GPU, and GNA devices; asymmetric weights and activations for VPU device. + # accuracy - the same as "mixed" for CPU, GPU, and GNA devices; asymmetric weights and activations for NPU device. "stat_subset_size": 300 # Size of the subset to calculate activations statistics that can be used # for quantization parameters calculation. } diff --git a/tools/pot/docs/DefaultQuantizationUsage.md b/tools/pot/docs/DefaultQuantizationUsage.md index 674d08ba815..ec2edbacca6 100644 --- a/tools/pot/docs/DefaultQuantizationUsage.md +++ b/tools/pot/docs/DefaultQuantizationUsage.md @@ -90,7 +90,7 @@ Default Quantization algorithm has mandatory and optional parameters which are d * ``"target_device"`` - the following options are available: - * ``"ANY"`` (or ``"CPU"``) - default option to quantize models for CPU, GPU, or VPU + * ``"ANY"`` (or ``"CPU"``) - default option to quantize models for CPU, GPU, or NPU * ``"CPU_SPR"`` - to quantize models for CPU SPR (4th Generation Intel® Xeon® Scalable processor family) * ``"GNA"``, ``"GNA3"``, ``"GNA3.5"`` - to quantize models for GNA devices respectively. diff --git a/tools/pot/openvino/tools/pot/algorithms/quantization/README.md b/tools/pot/openvino/tools/pot/algorithms/quantization/README.md index 0444889bf44..3b8b9f352e5 100644 --- a/tools/pot/openvino/tools/pot/algorithms/quantization/README.md +++ b/tools/pot/openvino/tools/pot/algorithms/quantization/README.md @@ -2,9 +2,9 @@ ## Introduction -The primary optimization feature of the Post-training Optimization Tool (POT) is the uniform integer quantization which allows substantially increasing inference performance and reducing the model size. Different HW platforms can support different integer precisions and POT is designed to support all of them, for example, 8-bit for CPU, GPU, VPU, 16-bit for GNA. Moreover, POT makes the specification of HW settings transparent for the user by introducing a concept of the `target_device` parameter. +The primary optimization feature of the Post-training Optimization Tool (POT) is the uniform integer quantization which allows substantially increasing inference performance and reducing the model size. Different HW platforms can support different integer precisions and POT is designed to support all of them, for example, 8-bit for CPU, GPU, NPU, 16-bit for GNA. Moreover, POT makes the specification of HW settings transparent for the user by introducing a concept of the `target_device` parameter. -> **NOTE**: There is a special `target_device: "ANY"` which leads to portable quantized models compatible with CPU, GPU, and VPU devices. GNA-quantized models are compatible only with CPU. +> **NOTE**: There is a special `target_device: "ANY"` which leads to portable quantized models compatible with CPU, GPU, and NPU devices. GNA-quantized models are compatible only with CPU. During the quantization process, the POT tool runs inference of the optimizing model to estimate quantization parameters for input activations of the quantizable operation. It means that a calibration dataset is required to perform quantization. This dataset may have or not have annotation depending on the quantization algorithm that is used. diff --git a/tools/pot/openvino/tools/pot/algorithms/quantization/accuracy_aware/algorithm.py b/tools/pot/openvino/tools/pot/algorithms/quantization/accuracy_aware/algorithm.py index d08c970f1af..b1c29d88872 100644 --- a/tools/pot/openvino/tools/pot/algorithms/quantization/accuracy_aware/algorithm.py +++ b/tools/pot/openvino/tools/pot/algorithms/quantization/accuracy_aware/algorithm.py @@ -17,7 +17,7 @@ class AccuracyAwareQuantization(Algorithm): algos_by_devices = { 'ANY': 'AccuracyAwareCommon', 'CPU': 'AccuracyAwareCommon', - 'VPU': 'AccuracyAwareCommon', + 'NPU': 'AccuracyAwareCommon', 'GPU': 'AccuracyAwareCommon', 'GNA': 'AccuracyAwareGNA', 'GNA3': 'AccuracyAwareGNA', diff --git a/tools/pot/openvino/tools/pot/algorithms/quantization/accuracy_aware_common/mixed_precision.py b/tools/pot/openvino/tools/pot/algorithms/quantization/accuracy_aware_common/mixed_precision.py index 70011eb9ccc..c99e9733fae 100644 --- a/tools/pot/openvino/tools/pot/algorithms/quantization/accuracy_aware_common/mixed_precision.py +++ b/tools/pot/openvino/tools/pot/algorithms/quantization/accuracy_aware_common/mixed_precision.py @@ -31,11 +31,11 @@ class INT4MixedQuantization(AccuracyAwareCommon): self.original_quantization_config.weights.bits = 8 self.original_quantization_config.activations.bits = 8 self._config.convert_to_mixed_preset = False - self._restrict_for_vpu = True + self._restrict_for_npu = True self._engine.calculate_metrics = True def _can_set_fq_to_low_bitwidth(self, node): - if self._restrict_for_vpu: + if self._restrict_for_npu: return (nu.get_node_output(node, 0)[0].type == 'Convolution') and \ ('group' not in nu.get_node_output(node, 0)[0]) return nu.get_node_output(node, 0)[0].type in OPERATIONS_WITH_WEIGHTS diff --git a/tools/pot/openvino/tools/pot/algorithms/quantization/fake_quantize_configuration.py b/tools/pot/openvino/tools/pot/algorithms/quantization/fake_quantize_configuration.py index 4642201b558..35733a07b84 100644 --- a/tools/pot/openvino/tools/pot/algorithms/quantization/fake_quantize_configuration.py +++ b/tools/pot/openvino/tools/pot/algorithms/quantization/fake_quantize_configuration.py @@ -528,7 +528,7 @@ def _fake_quantize_to_types(model, hardware_config): def change_configurations_by_model_type(model, config, fq_configuration, hardware_config): - if config['model_type'] == 'transformer' and config['target_device'] in ['ANY', 'CPU', 'CPU_SPR', 'GPU', 'VPU']: + if config['model_type'] == 'transformer' and config['target_device'] in ['ANY', 'CPU', 'CPU_SPR', 'GPU', 'NPU']: change_configurations_by_model_type_transformer(model, fq_configuration, hardware_config) diff --git a/tools/pot/openvino/tools/pot/algorithms/quantization/utils.py b/tools/pot/openvino/tools/pot/algorithms/quantization/utils.py index 9ad333a72bf..be69ad8bc63 100644 --- a/tools/pot/openvino/tools/pot/algorithms/quantization/utils.py +++ b/tools/pot/openvino/tools/pot/algorithms/quantization/utils.py @@ -21,7 +21,7 @@ __HARDWARE_CONFIGS_MAP = {'ANY': 'cpu.json', 'GNA3': 'gna3.json', 'GNA3.5': 'gna3.json', 'GPU': 'gpu.json', # Same as cpu.json but without LSTM/GRUSequence quantization - 'VPU': 'vpu.json', + 'NPU': 'npu.json', 'CPU_SPR': 'cpu.json'} diff --git a/tools/pot/openvino/tools/pot/configs/config.py b/tools/pot/openvino/tools/pot/configs/config.py index 9c55cbd8e49..0b5b41adc30 100644 --- a/tools/pot/openvino/tools/pot/configs/config.py +++ b/tools/pot/openvino/tools/pot/configs/config.py @@ -347,7 +347,7 @@ class Config(Dict): aliases = {'symmetric': 'performance', 'asymmetric': 'accuracy'} preset = aliases.get(preset, preset) presets_aliases_by_device = { - 'VPU': {'accuracy': 'accuracy'}, + 'NPU': {'accuracy': 'accuracy'}, 'GNA': {'accuracy': 'accuracy', 'mixed': 'accuracy'}, 'GNA3': {'accuracy': 'accuracy', 'mixed': 'accuracy'}, 'GNA3.5': {'accuracy': 'accuracy', 'mixed': 'accuracy'}, diff --git a/tools/pot/openvino/tools/pot/configs/hardware/vpu.json b/tools/pot/openvino/tools/pot/configs/hardware/npu.json similarity index 99% rename from tools/pot/openvino/tools/pot/configs/hardware/vpu.json rename to tools/pot/openvino/tools/pot/configs/hardware/npu.json index fbc1241fa5e..9fdf148d445 100644 --- a/tools/pot/openvino/tools/pot/configs/hardware/vpu.json +++ b/tools/pot/openvino/tools/pot/configs/hardware/npu.json @@ -1,5 +1,5 @@ { - "target_device": "VPU", + "target_device": "NPU", "config": { "quantization": { "q8_tn": { diff --git a/tools/pot/openvino/tools/pot/graph/vpu_patterns.py b/tools/pot/openvino/tools/pot/graph/npu_patterns.py similarity index 92% rename from tools/pot/openvino/tools/pot/graph/vpu_patterns.py rename to tools/pot/openvino/tools/pot/graph/npu_patterns.py index 5da9861a34e..44a7012f192 100644 --- a/tools/pot/openvino/tools/pot/graph/vpu_patterns.py +++ b/tools/pot/openvino/tools/pot/graph/npu_patterns.py @@ -4,7 +4,7 @@ from openvino.tools.pot.graph.pattern_utils import get_clamp_mult_const_pattern, \ get_softmax_reshape_transpose_gather_matmul_pattern -def get_vpu_ignored_patterns(): +def get_npu_ignored_patterns(): return { 'blocks': [get_softmax_reshape_transpose_gather_matmul_pattern()], 'activations': [get_clamp_mult_const_pattern()], diff --git a/tools/pot/openvino/tools/pot/graph/utils.py b/tools/pot/openvino/tools/pot/graph/utils.py index 30844760d58..1358c74ae9f 100644 --- a/tools/pot/openvino/tools/pot/graph/utils.py +++ b/tools/pot/openvino/tools/pot/graph/utils.py @@ -10,7 +10,7 @@ import numpy as np from openvino.tools.pot.version import get_version from .cpu_patterns import get_cpu_ignored_patterns, get_cpu_spr_ignored_patterns from .gpu_patterns import get_gpu_ignored_patterns -from .vpu_patterns import get_vpu_ignored_patterns +from .npu_patterns import get_npu_ignored_patterns from .gna_patterns import get_gna_ignored_patterns, get_gna3_ignored_patterns from .special_operations import QUANTIZE_AGNOSTIC_OPERATIONS from .node_utils import get_all_node_outputs, get_input_shape @@ -19,7 +19,7 @@ HARDWARE_AWARE_IGNORED_PATTERNS = { 'ANY': get_cpu_ignored_patterns(), 'CPU': get_cpu_ignored_patterns(), 'GPU': get_gpu_ignored_patterns(), - 'VPU': get_vpu_ignored_patterns(), + 'NPU': get_npu_ignored_patterns(), 'GNA': get_gna_ignored_patterns(), 'GNA3': get_gna3_ignored_patterns(), 'GNA3.5': get_gna3_ignored_patterns(), diff --git a/tools/pot/tests/test_target_device.py b/tools/pot/tests/test_target_device.py index d42d294c8ae..2e6a8e429b1 100644 --- a/tools/pot/tests/test_target_device.py +++ b/tools/pot/tests/test_target_device.py @@ -7,7 +7,7 @@ from .utils.path import TOOL_CONFIG_PATH DEVICE = [ 'CPU', 'GPU', - 'VPU' + 'NPU' ] diff --git a/tools/pot/tests/test_unify_scales.py b/tools/pot/tests/test_unify_scales.py index 3d8ade75de2..abd829ac026 100644 --- a/tools/pot/tests/test_unify_scales.py +++ b/tools/pot/tests/test_unify_scales.py @@ -18,9 +18,9 @@ from .utils.path import TEST_ROOT from .utils.data_helper import load_json TEST_MODELS = [ - ('mobilenet-v2-pytorch', 'pytorch', 'MinMaxQuantization', 'performance', 'VPU'), - ('resnet-50-tf', 'tf', 'DefaultQuantization', 'performance', 'VPU'), - ('octave-resnet-26-0.25', 'mxnet', 'DefaultQuantization', 'accuracy', 'VPU'), + ('mobilenet-v2-pytorch', 'pytorch', 'MinMaxQuantization', 'performance', 'NPU'), + ('resnet-50-tf', 'tf', 'DefaultQuantization', 'performance', 'NPU'), + ('octave-resnet-26-0.25', 'mxnet', 'DefaultQuantization', 'accuracy', 'NPU'), ('concat_depthwise_model', 'pytorch', 'MinMaxQuantization', 'accuracy', 'CPU'), ]