Browse Source
!1603 code_sync_0428_inc
From: @ding_fei_fei Reviewed-by: @liucunwei,@ljl0711 Signed-off-by: @liucunweitags/v1.3.0
mindspore-ci-bot
Gitee
4 years ago
18 changed files with 353 additions and 213 deletions
Split View
Diff Options
-
+37 -34inc/external/acl/error_codes/rt_error_codes.h
-
+37 -34inc/external/runtime/rt_error_codes.h
-
+16 -0third_party/fwkacllib/inc/ops/data_flow_ops.h
-
+8 -6third_party/fwkacllib/inc/ops/elewise_calculation_ops.h
-
+8 -5third_party/fwkacllib/inc/ops/image_ops.h
-
+31 -0third_party/fwkacllib/inc/ops/matrix_calculation_ops.h
-
+0 -28third_party/fwkacllib/inc/ops/nn_batch_norm_ops.h
-
+3 -0third_party/fwkacllib/inc/ops/nn_calculation_ops.h
-
+24 -29third_party/fwkacllib/inc/ops/nn_detect_ops.h
-
+22 -22third_party/fwkacllib/inc/ops/nn_norm_ops.h
-
+50 -9third_party/fwkacllib/inc/ops/nn_pooling_ops.h
-
+49 -0third_party/fwkacllib/inc/ops/nn_training_ops.h
-
+9 -9third_party/fwkacllib/inc/ops/parsing_ops.h
-
+2 -0third_party/fwkacllib/inc/ops/random_ops.h
-
+23 -12third_party/fwkacllib/inc/ops/rnn.h
-
+27 -0third_party/fwkacllib/inc/ops/selection_ops.h
-
+2 -0third_party/fwkacllib/inc/ops/string_ops.h
-
+5 -25third_party/fwkacllib/inc/toolchain/tuning_tool/tune_api.h
+ 37
- 34
inc/external/acl/error_codes/rt_error_codes.h
View File
| @@ -57,40 +57,43 @@ static const int32_t ACL_ERROR_RT_NO_STREAM_RESOURCE = 207008; // no stream re | |||
| static const int32_t ACL_ERROR_RT_NO_NOTIFY_RESOURCE = 207009; // no notify resource | |||
| static const int32_t ACL_ERROR_RT_NO_MODEL_RESOURCE = 207010; // no model resource | |||
| static const int32_t ACL_ERROR_RT_INTERNAL_ERROR = 507000; // runtime internal error | |||
| static const int32_t ACL_ERROR_RT_TS_ERROR = 507001; // ts internel error | |||
| static const int32_t ACL_ERROR_RT_STREAM_TASK_FULL = 507002; // task full in stream | |||
| static const int32_t ACL_ERROR_RT_STREAM_TASK_EMPTY = 507003; // task empty in stream | |||
| static const int32_t ACL_ERROR_RT_STREAM_NOT_COMPLETE = 507004; // stream not complete | |||
| static const int32_t ACL_ERROR_RT_END_OF_SEQUENCE = 507005; // end of sequence | |||
| static const int32_t ACL_ERROR_RT_EVENT_NOT_COMPLETE = 507006; // event not complete | |||
| static const int32_t ACL_ERROR_RT_CONTEXT_RELEASE_ERROR = 507007; // context release error | |||
| static const int32_t ACL_ERROR_RT_SOC_VERSION = 507008; // soc version error | |||
| static const int32_t ACL_ERROR_RT_TASK_TYPE_NOT_SUPPORT = 507009; // task type not support | |||
| static const int32_t ACL_ERROR_RT_LOST_HEARTBEAT = 507010; // ts lost heartbeat | |||
| static const int32_t ACL_ERROR_RT_MODEL_EXECUTE = 507011; // model execute failed | |||
| static const int32_t ACL_ERROR_RT_REPORT_TIMEOUT = 507012; // report timeout | |||
| static const int32_t ACL_ERROR_RT_SYS_DMA = 507013; // sys dma error | |||
| static const int32_t ACL_ERROR_RT_AICORE_TIMEOUT = 507014; // aicore timeout | |||
| static const int32_t ACL_ERROR_RT_AICORE_EXCEPTION = 507015; // aicore exception | |||
| static const int32_t ACL_ERROR_RT_AICORE_TRAP_EXCEPTION = 507016; // aicore trap exception | |||
| static const int32_t ACL_ERROR_RT_AICPU_TIMEOUT = 507017; // aicpu timeout | |||
| static const int32_t ACL_ERROR_RT_AICPU_EXCEPTION = 507018; // aicpu exception | |||
| static const int32_t ACL_ERROR_RT_AICPU_DATADUMP_RSP_ERR = 507019; // aicpu datadump response error | |||
| static const int32_t ACL_ERROR_RT_AICPU_MODEL_RSP_ERR = 507020; // aicpu model operate response error | |||
| static const int32_t ACL_ERROR_RT_PROFILING_ERROR = 507021; // profiling error | |||
| static const int32_t ACL_ERROR_RT_IPC_ERROR = 507022; // ipc error | |||
| static const int32_t ACL_ERROR_RT_MODEL_ABORT_NORMAL = 507023; // model abort normal | |||
| static const int32_t ACL_ERROR_RT_KERNEL_UNREGISTERING = 507024; // kernel unregistering | |||
| static const int32_t ACL_ERROR_RT_RINGBUFFER_NOT_INIT = 507025; // ringbuffer not init | |||
| static const int32_t ACL_ERROR_RT_RINGBUFFER_NO_DATA = 507026; // ringbuffer no data | |||
| static const int32_t ACL_ERROR_RT_KERNEL_LOOKUP = 507027; // kernel lookup error | |||
| static const int32_t ACL_ERROR_RT_KERNEL_DUPLICATE = 507028; // kernel register duplicate | |||
| static const int32_t ACL_ERROR_RT_DEBUG_REGISTER_FAIL = 507029; // debug register failed | |||
| static const int32_t ACL_ERROR_RT_DEBUG_UNREGISTER_FAIL = 507030; // debug unregister failed | |||
| static const int32_t ACL_ERROR_RT_LABEL_CONTEXT = 507031; // label not in current context | |||
| static const int32_t ACL_ERROR_RT_PROGRAM_USE_OUT = 507032; // program register num use out | |||
| static const int32_t ACL_ERROR_RT_DEV_SETUP_ERROR = 507033; // device setup error | |||
| static const int32_t ACL_ERROR_RT_INTERNAL_ERROR = 507000; // runtime internal error | |||
| static const int32_t ACL_ERROR_RT_TS_ERROR = 507001; // ts internel error | |||
| static const int32_t ACL_ERROR_RT_STREAM_TASK_FULL = 507002; // task full in stream | |||
| static const int32_t ACL_ERROR_RT_STREAM_TASK_EMPTY = 507003; // task empty in stream | |||
| static const int32_t ACL_ERROR_RT_STREAM_NOT_COMPLETE = 507004; // stream not complete | |||
| static const int32_t ACL_ERROR_RT_END_OF_SEQUENCE = 507005; // end of sequence | |||
| static const int32_t ACL_ERROR_RT_EVENT_NOT_COMPLETE = 507006; // event not complete | |||
| static const int32_t ACL_ERROR_RT_CONTEXT_RELEASE_ERROR = 507007; // context release error | |||
| static const int32_t ACL_ERROR_RT_SOC_VERSION = 507008; // soc version error | |||
| static const int32_t ACL_ERROR_RT_TASK_TYPE_NOT_SUPPORT = 507009; // task type not support | |||
| static const int32_t ACL_ERROR_RT_LOST_HEARTBEAT = 507010; // ts lost heartbeat | |||
| static const int32_t ACL_ERROR_RT_MODEL_EXECUTE = 507011; // model execute failed | |||
| static const int32_t ACL_ERROR_RT_REPORT_TIMEOUT = 507012; // report timeout | |||
| static const int32_t ACL_ERROR_RT_SYS_DMA = 507013; // sys dma error | |||
| static const int32_t ACL_ERROR_RT_AICORE_TIMEOUT = 507014; // aicore timeout | |||
| static const int32_t ACL_ERROR_RT_AICORE_EXCEPTION = 507015; // aicore exception | |||
| static const int32_t ACL_ERROR_RT_AICORE_TRAP_EXCEPTION = 507016; // aicore trap exception | |||
| static const int32_t ACL_ERROR_RT_AICPU_TIMEOUT = 507017; // aicpu timeout | |||
| static const int32_t ACL_ERROR_RT_AICPU_EXCEPTION = 507018; // aicpu exception | |||
| static const int32_t ACL_ERROR_RT_AICPU_DATADUMP_RSP_ERR = 507019; // aicpu datadump response error | |||
| static const int32_t ACL_ERROR_RT_AICPU_MODEL_RSP_ERR = 507020; // aicpu model operate response error | |||
| static const int32_t ACL_ERROR_RT_PROFILING_ERROR = 507021; // profiling error | |||
| static const int32_t ACL_ERROR_RT_IPC_ERROR = 507022; // ipc error | |||
| static const int32_t ACL_ERROR_RT_MODEL_ABORT_NORMAL = 507023; // model abort normal | |||
| static const int32_t ACL_ERROR_RT_KERNEL_UNREGISTERING = 507024; // kernel unregistering | |||
| static const int32_t ACL_ERROR_RT_RINGBUFFER_NOT_INIT = 507025; // ringbuffer not init | |||
| static const int32_t ACL_ERROR_RT_RINGBUFFER_NO_DATA = 507026; // ringbuffer no data | |||
| static const int32_t ACL_ERROR_RT_KERNEL_LOOKUP = 507027; // kernel lookup error | |||
| static const int32_t ACL_ERROR_RT_KERNEL_DUPLICATE = 507028; // kernel register duplicate | |||
| static const int32_t ACL_ERROR_RT_DEBUG_REGISTER_FAIL = 507029; // debug register failed | |||
| static const int32_t ACL_ERROR_RT_DEBUG_UNREGISTER_FAIL = 507030; // debug unregister failed | |||
| static const int32_t ACL_ERROR_RT_LABEL_CONTEXT = 507031; // label not in current context | |||
| static const int32_t ACL_ERROR_RT_PROGRAM_USE_OUT = 507032; // program register num use out | |||
| static const int32_t ACL_ERROR_RT_DEV_SETUP_ERROR = 507033; // device setup error | |||
| static const int32_t ACL_ERROR_RT_VECTOR_CORE_TIMEOUT = 507034; // vector core timeout | |||
| static const int32_t ACL_ERROR_RT_VECTOR_CORE_EXCEPTION = 507035; // vector core exception | |||
| static const int32_t ACL_ERROR_RT_VECTOR_CORE_TRAP_EXCEPTION = 507036; // vector core trap exception | |||
| static const int32_t ACL_ERROR_RT_DRV_INTERNAL_ERROR = 507899; // drv internal error | |||
| static const int32_t ACL_ERROR_RT_AICPU_INTERNAL_ERROR = 507900; // aicpu internal error | |||
+ 37
- 34
inc/external/runtime/rt_error_codes.h
View File
| @@ -57,40 +57,43 @@ static const int32_t ACL_ERROR_RT_NO_STREAM_RESOURCE = 207008; // no stream re | |||
| static const int32_t ACL_ERROR_RT_NO_NOTIFY_RESOURCE = 207009; // no notify resource | |||
| static const int32_t ACL_ERROR_RT_NO_MODEL_RESOURCE = 207010; // no model resource | |||
| static const int32_t ACL_ERROR_RT_INTERNAL_ERROR = 507000; // runtime internal error | |||
| static const int32_t ACL_ERROR_RT_TS_ERROR = 507001; // ts internel error | |||
| static const int32_t ACL_ERROR_RT_STREAM_TASK_FULL = 507002; // task full in stream | |||
| static const int32_t ACL_ERROR_RT_STREAM_TASK_EMPTY = 507003; // task empty in stream | |||
| static const int32_t ACL_ERROR_RT_STREAM_NOT_COMPLETE = 507004; // stream not complete | |||
| static const int32_t ACL_ERROR_RT_END_OF_SEQUENCE = 507005; // end of sequence | |||
| static const int32_t ACL_ERROR_RT_EVENT_NOT_COMPLETE = 507006; // event not complete | |||
| static const int32_t ACL_ERROR_RT_CONTEXT_RELEASE_ERROR = 507007; // context release error | |||
| static const int32_t ACL_ERROR_RT_SOC_VERSION = 507008; // soc version error | |||
| static const int32_t ACL_ERROR_RT_TASK_TYPE_NOT_SUPPORT = 507009; // task type not support | |||
| static const int32_t ACL_ERROR_RT_LOST_HEARTBEAT = 507010; // ts lost heartbeat | |||
| static const int32_t ACL_ERROR_RT_MODEL_EXECUTE = 507011; // model execute failed | |||
| static const int32_t ACL_ERROR_RT_REPORT_TIMEOUT = 507012; // report timeout | |||
| static const int32_t ACL_ERROR_RT_SYS_DMA = 507013; // sys dma error | |||
| static const int32_t ACL_ERROR_RT_AICORE_TIMEOUT = 507014; // aicore timeout | |||
| static const int32_t ACL_ERROR_RT_AICORE_EXCEPTION = 507015; // aicore exception | |||
| static const int32_t ACL_ERROR_RT_AICORE_TRAP_EXCEPTION = 507016; // aicore trap exception | |||
| static const int32_t ACL_ERROR_RT_AICPU_TIMEOUT = 507017; // aicpu timeout | |||
| static const int32_t ACL_ERROR_RT_AICPU_EXCEPTION = 507018; // aicpu exception | |||
| static const int32_t ACL_ERROR_RT_AICPU_DATADUMP_RSP_ERR = 507019; // aicpu datadump response error | |||
| static const int32_t ACL_ERROR_RT_AICPU_MODEL_RSP_ERR = 507020; // aicpu model operate response error | |||
| static const int32_t ACL_ERROR_RT_PROFILING_ERROR = 507021; // profiling error | |||
| static const int32_t ACL_ERROR_RT_IPC_ERROR = 507022; // ipc error | |||
| static const int32_t ACL_ERROR_RT_MODEL_ABORT_NORMAL = 507023; // model abort normal | |||
| static const int32_t ACL_ERROR_RT_KERNEL_UNREGISTERING = 507024; // kernel unregistering | |||
| static const int32_t ACL_ERROR_RT_RINGBUFFER_NOT_INIT = 507025; // ringbuffer not init | |||
| static const int32_t ACL_ERROR_RT_RINGBUFFER_NO_DATA = 507026; // ringbuffer no data | |||
| static const int32_t ACL_ERROR_RT_KERNEL_LOOKUP = 507027; // kernel lookup error | |||
| static const int32_t ACL_ERROR_RT_KERNEL_DUPLICATE = 507028; // kernel register duplicate | |||
| static const int32_t ACL_ERROR_RT_DEBUG_REGISTER_FAIL = 507029; // debug register failed | |||
| static const int32_t ACL_ERROR_RT_DEBUG_UNREGISTER_FAIL = 507030; // debug unregister failed | |||
| static const int32_t ACL_ERROR_RT_LABEL_CONTEXT = 507031; // label not in current context | |||
| static const int32_t ACL_ERROR_RT_PROGRAM_USE_OUT = 507032; // program register num use out | |||
| static const int32_t ACL_ERROR_RT_DEV_SETUP_ERROR = 507033; // device setup error | |||
| static const int32_t ACL_ERROR_RT_INTERNAL_ERROR = 507000; // runtime internal error | |||
| static const int32_t ACL_ERROR_RT_TS_ERROR = 507001; // ts internel error | |||
| static const int32_t ACL_ERROR_RT_STREAM_TASK_FULL = 507002; // task full in stream | |||
| static const int32_t ACL_ERROR_RT_STREAM_TASK_EMPTY = 507003; // task empty in stream | |||
| static const int32_t ACL_ERROR_RT_STREAM_NOT_COMPLETE = 507004; // stream not complete | |||
| static const int32_t ACL_ERROR_RT_END_OF_SEQUENCE = 507005; // end of sequence | |||
| static const int32_t ACL_ERROR_RT_EVENT_NOT_COMPLETE = 507006; // event not complete | |||
| static const int32_t ACL_ERROR_RT_CONTEXT_RELEASE_ERROR = 507007; // context release error | |||
| static const int32_t ACL_ERROR_RT_SOC_VERSION = 507008; // soc version error | |||
| static const int32_t ACL_ERROR_RT_TASK_TYPE_NOT_SUPPORT = 507009; // task type not support | |||
| static const int32_t ACL_ERROR_RT_LOST_HEARTBEAT = 507010; // ts lost heartbeat | |||
| static const int32_t ACL_ERROR_RT_MODEL_EXECUTE = 507011; // model execute failed | |||
| static const int32_t ACL_ERROR_RT_REPORT_TIMEOUT = 507012; // report timeout | |||
| static const int32_t ACL_ERROR_RT_SYS_DMA = 507013; // sys dma error | |||
| static const int32_t ACL_ERROR_RT_AICORE_TIMEOUT = 507014; // aicore timeout | |||
| static const int32_t ACL_ERROR_RT_AICORE_EXCEPTION = 507015; // aicore exception | |||
| static const int32_t ACL_ERROR_RT_AICORE_TRAP_EXCEPTION = 507016; // aicore trap exception | |||
| static const int32_t ACL_ERROR_RT_AICPU_TIMEOUT = 507017; // aicpu timeout | |||
| static const int32_t ACL_ERROR_RT_AICPU_EXCEPTION = 507018; // aicpu exception | |||
| static const int32_t ACL_ERROR_RT_AICPU_DATADUMP_RSP_ERR = 507019; // aicpu datadump response error | |||
| static const int32_t ACL_ERROR_RT_AICPU_MODEL_RSP_ERR = 507020; // aicpu model operate response error | |||
| static const int32_t ACL_ERROR_RT_PROFILING_ERROR = 507021; // profiling error | |||
| static const int32_t ACL_ERROR_RT_IPC_ERROR = 507022; // ipc error | |||
| static const int32_t ACL_ERROR_RT_MODEL_ABORT_NORMAL = 507023; // model abort normal | |||
| static const int32_t ACL_ERROR_RT_KERNEL_UNREGISTERING = 507024; // kernel unregistering | |||
| static const int32_t ACL_ERROR_RT_RINGBUFFER_NOT_INIT = 507025; // ringbuffer not init | |||
| static const int32_t ACL_ERROR_RT_RINGBUFFER_NO_DATA = 507026; // ringbuffer no data | |||
| static const int32_t ACL_ERROR_RT_KERNEL_LOOKUP = 507027; // kernel lookup error | |||
| static const int32_t ACL_ERROR_RT_KERNEL_DUPLICATE = 507028; // kernel register duplicate | |||
| static const int32_t ACL_ERROR_RT_DEBUG_REGISTER_FAIL = 507029; // debug register failed | |||
| static const int32_t ACL_ERROR_RT_DEBUG_UNREGISTER_FAIL = 507030; // debug unregister failed | |||
| static const int32_t ACL_ERROR_RT_LABEL_CONTEXT = 507031; // label not in current context | |||
| static const int32_t ACL_ERROR_RT_PROGRAM_USE_OUT = 507032; // program register num use out | |||
| static const int32_t ACL_ERROR_RT_DEV_SETUP_ERROR = 507033; // device setup error | |||
| static const int32_t ACL_ERROR_RT_VECTOR_CORE_TIMEOUT = 507034; // vector core timeout | |||
| static const int32_t ACL_ERROR_RT_VECTOR_CORE_EXCEPTION = 507035; // vector core exception | |||
| static const int32_t ACL_ERROR_RT_VECTOR_CORE_TRAP_EXCEPTION = 507036; // vector core trap exception | |||
| static const int32_t ACL_ERROR_RT_DRV_INTERNAL_ERROR = 507899; // drv internal error | |||
| static const int32_t ACL_ERROR_RT_AICPU_INTERNAL_ERROR = 507900; // aicpu internal error | |||
+ 16
- 0
third_party/fwkacllib/inc/ops/data_flow_ops.h
View File
| @@ -2331,6 +2331,22 @@ REG_OP(CacheAllIndexToLocal) | |||
| .REQUIRED_ATTR(dtype, Type) | |||
| .OP_END_FACTORY_REG(CacheAllIndexToLocal) | |||
| /** | |||
| *@brief DynamicGetNext, dynamic get next data | |||
| *@par Inputs: | |||
| *x: the iterator, all types are available | |||
| *@par Outputs: | |||
| *y: the date in iterator, all types are available | |||
| *@par Attributes: | |||
| *output_types: types of all outputs | |||
| *output_shapes: shapes of all outputs | |||
| *_dynamic_graph_execute_mode: dynamic graph execution mode, | |||
| value is one of lazy_recompile and dynamic_execute | |||
| *_getnext_inputs_shape_range: shape ranges of outputs, | |||
| it works where _dynamic_graph_execute_mode is dynamic_execute | |||
| *@par Restrictions: | |||
| *Warning: THIS FUNCTION IS EXPERIMENTAL. Please do not use. | |||
| */ | |||
| REG_OP(DynamicGetNext) | |||
| .INPUT(x, TensorType::ALL()) | |||
| .DYNAMIC_OUTPUT(y, TensorType::ALL()) | |||
+ 8
- 6
third_party/fwkacllib/inc/ops/elewise_calculation_ops.h
View File
| @@ -28,7 +28,7 @@ namespace ge { | |||
| *@par Inputs: | |||
| *Dynamic inputs, including: | |||
| * @li x: A list of Tensor objects, each with same shape and type. The supported types are: | |||
| *x: A list of Tensor objects, each with same shape and type. The supported types are: | |||
| * float16, float32, double, int32, uint8, int16, int8, complex64, int64, | |||
| * qint8, quint8, qint32, uint16, complex128, uint32, uint64. It's a dynamic input. \n | |||
| @@ -330,8 +330,8 @@ REG_OP(Sub) | |||
| *@brief computes the absolute value of a tensor. \n | |||
| *@par Inputs: | |||
| *One inputs, including: | |||
| * @li x: A Tensor. Must be one of the following types: float16, float32, double, int32, int64. \n | |||
| *One input, including: \n | |||
| *x: A Tensor. Must be one of the following types: float16, float32, double, int32, int64. \n | |||
| *@par Outputs: | |||
| *y: A Tensor. Has the same type as "x". \n | |||
| @@ -3243,9 +3243,11 @@ REG_OP(Fills) | |||
| *@brief Add tensor with scale. \n | |||
| *@par Inputs: | |||
| *Five inputs, including: | |||
| * @li x1: A Tensor. Must be one of the following types:int32,int16, float16, float32. | |||
| * @li x2: A scale. Must be float. \n | |||
| *One input, including: \n | |||
| *x: A Tensor. Must be one of the following types:int32,int16, float16, float32. \n | |||
| *@par Attributes: | |||
| *value: A scale. Must be float. \n | |||
| *@par Outputs: | |||
| *@li y: A Tensor. Has the same type and shape as "x1". \n | |||
+ 8
- 5
third_party/fwkacllib/inc/ops/image_ops.h
View File
| @@ -1134,7 +1134,7 @@ REG_OP(DecodeBmp) | |||
| .ATTR(channels, Int, 0) | |||
| .OP_END_FACTORY_REG(DecodeBmp) | |||
| /* | |||
| /** | |||
| *@brief Function parse image from string to int. \n | |||
| *@par Inputs: | |||
| @@ -1602,11 +1602,11 @@ REG_OP(DecodeJpeg) | |||
| *@brief Image warping using per-pixel flow vectors. \n | |||
| *@par Inputs: | |||
| *@li images: 4-D Tensor with shape `[batch, height, width, channels]`. | |||
| *@li image: 4-D Tensor with shape `[batch, height, width, channels]`. | |||
| *@li flow: 4-D Tensor with shape `[batch, height, width, 2]`. \n | |||
| *@par Outputs: | |||
| *y: Returns 4-D with the same shape and dtype as `images`. \n | |||
| *y: Returns 4-D with the same shape and dtype as `image`. \n | |||
| */ | |||
| REG_OP(DenseImageWarp) | |||
| .INPUT(image, TensorType({DT_FLOAT, DT_FLOAT16})) | |||
| @@ -1709,11 +1709,11 @@ REG_OP(ResizeGradD) | |||
| *@par Inputs: | |||
| *@li grad: gradients with respect to DenseImageWarp output. | |||
| *@li images: 4-D Tensor with shape `[batch, height, width, channels]`. | |||
| *@li image: 4-D Tensor with shape `[batch, height, width, channels]`. | |||
| *@li flow: 4-D Tensor with shape `[batch, height, width, 2]`. \n | |||
| *@par Outputs: | |||
| *grad_image: Returns 4-D with the same shape and dtype as `images`. | |||
| *grad_image: Returns 4-D with the same shape and dtype as `image`. | |||
| *grad_flow: Returns 4-D with the same shape and dtype as `flow`. \n | |||
| */ | |||
| REG_OP(DenseImageWarpGrad) | |||
| @@ -1747,6 +1747,9 @@ REG_OP(DenseImageWarpGrad) | |||
| *@par Third-party framework compatibility | |||
| *Compatible with pytorch GridSampler2D operator. | |||
| *@par Restrictions: | |||
| *Warning:THIS FUNCTION IS EXPERIMENTAL. Please do not use. | |||
| */ | |||
| REG_OP(GridSampler2D) | |||
| .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT})) | |||
+ 31
- 0
third_party/fwkacllib/inc/ops/matrix_calculation_ops.h
View File
| @@ -444,6 +444,9 @@ REG_OP(ScatterNdUpdate) | |||
| *@par Third-party framework compatibility | |||
| * Compatible with the TensorFlow operator TensorScatterUpdate. | |||
| *@par Restrictions: | |||
| *Warning: THIS FUNCTION IS EXPERIMENTAL. Please do not use. | |||
| */ | |||
| REG_OP(TensorScatterUpdate) | |||
| .INPUT(x, TensorType::BasicType()) | |||
| @@ -565,6 +568,9 @@ REG_OP(ScatterNdAdd) | |||
| *@par Third-party framework compatibility | |||
| * Compatible with the TensorFlow operator TensorScatterAdd. | |||
| *@par Restrictions: | |||
| *Warning: THIS FUNCTION IS EXPERIMENTAL. Please do not use. | |||
| */ | |||
| REG_OP(TensorScatterAdd) | |||
| .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT,DT_INT32,DT_INT8,DT_UINT8})) | |||
| @@ -623,6 +629,9 @@ REG_OP(ScatterNdSub) | |||
| *@par Third-party framework compatibility | |||
| * Compatible with the TensorFlow operator TensorScatterSub. | |||
| *@par Restrictions: | |||
| *Warning: THIS FUNCTION IS EXPERIMENTAL. Please do not use. | |||
| */ | |||
| REG_OP(TensorScatterSub) | |||
| .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT,DT_INT32,DT_INT8,DT_UINT8})) | |||
| @@ -1045,6 +1054,28 @@ REG_OP(MatrixDiagV2) | |||
| .OUTPUT(output, TensorType::BasicType()) | |||
| .OP_END_FACTORY_REG(MatrixDiagV2) | |||
| /** | |||
| * @brief Add updates to var_out according to axis and indices. | |||
| * @par Inputs: | |||
| * Three inputs, including: | |||
| * @li var: A Tensor. Must be one of the following types: | |||
| * float16, float32, int32, int8, uint8. | |||
| * @li indices: A Tensor of the indices, type should be int32. | |||
| * @li updates: A Tensor of the same type as "var". | |||
| * @par Attributes: | |||
| * @li axis: An required int to specify the axis to perform indices add. | |||
| * @par Outputs: | |||
| * @li var_out: A Tensor. Same as input "var". | |||
| * @par Third-party framework compatibility | |||
| * Compatible with the Pytorch operator index_add. | |||
| * @par Restrictions: | |||
| * Warning:THIS FUNCTION IS EXPERIMENTAL. Please do not use. | |||
| */ | |||
| REG_OP(IndexAdd) | |||
| .INPUT(var, TensorType({DT_INT32, DT_INT8, DT_UINT8, DT_FLOAT32, DT_FLOAT16})) | |||
| .INPUT(indices, TensorType({DT_INT32})) | |||
+ 0
- 28
third_party/fwkacllib/inc/ops/nn_batch_norm_ops.h
View File
| @@ -419,35 +419,7 @@ REG_OP(BNInference) | |||
| .ATTR(use_global_stats, Bool,true) | |||
| .ATTR(mode, Int,1) | |||
| .OP_END_FACTORY_REG(BNInference) | |||
| /** | |||
| *@brief aicpu batch normalization host . \n | |||
| *@par Inputs: | |||
| *@li mean: A Tensor of type float32 or float16. Must be 1D if input "x" Specifies the mean used for inference. | |||
| *@li variance: A Tensor of type float32 or float16 . Must be 1D if input "x" Specifies the variance used for inference. | |||
| *@li momentum: An optional float, mean and variance's Scale factor | |||
| *@par Attributes: | |||
| *@li epsilon: An optional float32, specifying the small value added to variance to avoid dividing by zero. Defaults to "0.00001". | |||
| *@li use_global_stats: mean inference mode , only can be "True". | |||
| *@li mode: An optional attr, not use | |||
| *@par Outputs: | |||
| *@li alpha: A Tensor of type float16 or float32 for the cpu calculate mean | |||
| *@li beta: A Tensor of type float16 or float32 for the cpu calculate variance | |||
| */ | |||
| REG_OP(BnHost) | |||
| .INPUT(mean, TensorType({DT_FLOAT, DT_FLOAT16})) | |||
| .INPUT(variance, TensorType({DT_FLOAT, DT_FLOAT16})) | |||
| .INPUT(momentum, TensorType({DT_FLOAT16,DT_FLOAT})) | |||
| .OPTIONAL_INPUT(scale, TensorType({DT_FLOAT16,DT_FLOAT})) | |||
| .OPTIONAL_INPUT(offset, TensorType({DT_FLOAT16,DT_FLOAT})) | |||
| .ATTR(epsilon, Float, 0.00001) | |||
| .ATTR(mode, Int, 1) | |||
| .ATTR(use_global_stats, Bool, true) | |||
| .OUTPUT(alpha, TensorType({DT_FLOAT, DT_FLOAT16})) | |||
| .OUTPUT(beta, TensorType({DT_FLOAT, DT_FLOAT16})) | |||
| .OUTPUT(mu, TensorType({DT_FLOAT16,DT_FLOAT})) | |||
| .OP_END_FACTORY_REG(BnHost) | |||
| /** | |||
| *@brief Performs batch normalization . \n | |||
+ 3
- 0
third_party/fwkacllib/inc/ops/nn_calculation_ops.h
View File
| @@ -989,6 +989,8 @@ REG_OP(Conv2DCompress) | |||
| *@li deformable_groups: Optional. An integer of type int32. The number of | |||
| * deformable group partitions. In_channels must be divisible by | |||
| * "deformable_groups". Defaults to 1. | |||
| *@li modulated: Optional. Specify version of DeformableConv2D, true means v2, | |||
| * false means v1, currently only support v2. | |||
| *\n | |||
| *\n | |||
| * The following value range restrictions must be met: | |||
| @@ -1037,6 +1039,7 @@ REG_OP(DeformableConv2D) | |||
| .ATTR(groups, Int, 1) | |||
| .ATTR(data_format, String, "NHWC") | |||
| .ATTR(deformable_groups, Int, 1) | |||
| .ATTR(modulated, Bool, true) | |||
| .OP_END_FACTORY_REG(DeformableConv2D) | |||
| /** | |||
+ 24
- 29
third_party/fwkacllib/inc/ops/nn_detect_ops.h
View File
| @@ -1202,35 +1202,6 @@ REG_OP(RpnProposalsD) | |||
| .OUTPUT(sorted_box, TensorType({DT_FLOAT16})) | |||
| .OP_END_FACTORY_REG(RpnProposalsD) | |||
| /** | |||
| *@brief Computes Score Filte Pre-Sort function. | |||
| *@par Inputs: | |||
| *Inputs include: | |||
| * @li rois: A Tensor. Must be float16. N-D with shape [N, 4]. | |||
| * @li cls_bg_prob: A Tensor. Must be float16. N-D with shape [N, 1]. | |||
| *@par Attributes: | |||
| * @li score_threshold: required, float, threahold of topk process. | |||
| * @li k: required, Int, threahold of topk process. | |||
| * @li score_filter: bool, mark of score_filter. Defaults to "true" | |||
| * @li core_max_num: int, max number of core. Defaults to "8" | |||
| *@par Outputs: | |||
| * @li sorted_proposal: A Tensor. Must be float16. | |||
| * N-D with shape [8*6002, 8]. | |||
| * @li proposal_num: A Tensor. Must be uint32. N-D with shape [8, 8]. | |||
| */ | |||
| REG_OP(ScoreFiltePreSort) | |||
| .INPUT(rois, TensorType({DT_FLOAT16})) | |||
| .INPUT(cls_bg_prob, TensorType({DT_FLOAT16})) | |||
| .OUTPUT(sorted_proposal, TensorType({ DT_FLOAT16})) | |||
| .OUTPUT(proposal_num, TensorType({ DT_UINT32})) | |||
| .REQUIRED_ATTR(score_threshold, Float) | |||
| .REQUIRED_ATTR(k, Int) | |||
| .ATTR(score_filter, Bool, true) | |||
| .ATTR(core_max_num, Int, 8) | |||
| .OP_END_FACTORY_REG(ScoreFiltePreSort) | |||
| /** | |||
| *@brief Computes Score Filte Pre-Sort function. | |||
| @@ -1500,6 +1471,26 @@ REG_OP(Sort) | |||
| .ATTR(descending, Bool, false) | |||
| .OP_END_FACTORY_REG(Sort) | |||
| /** | |||
| *@brief Computes iou for input bboxes and gtboxes. | |||
| *@par Inputs: | |||
| * Two inputs, including: | |||
| *@li bboxes: boxes, a 4D Tensor of type float16 with the shape (x0, x1, y0, y1), | |||
| *@li gtboxes: boxes, a 4D Tensor of type float16 with the shape (x0, x1, y0, y1).\n | |||
| *@par Attributes: | |||
| *@li mode: A optional attribute of type string, whether judge the mode of iou. \n | |||
| *@par Outputs: | |||
| *@li overlap: A 2D Tensor of type float16 with shape [n, m]. \n | |||
| *@attention Constraints: | |||
| * Only computation of float16 data is supported. | |||
| *@par Restrictions: | |||
| *Warning:THIS FUNCTION IS DEPRECATED. Please use Iou instead. | |||
| */ | |||
| REG_OP(PtIou) | |||
| .INPUT(bboxes, TensorType({DT_FLOAT16, DT_FLOAT})) | |||
| .INPUT(gtboxes, TensorType({DT_FLOAT16, DT_FLOAT})) | |||
| @@ -1541,6 +1532,9 @@ selected indices from the boxes tensor, where M <= max_output_size. \n | |||
| *@par Third-party framework compatibility | |||
| *Compatible with onnx NonMaxSuppression operator. | |||
| *@par Restrictions: | |||
| *Warning:THIS FUNCTION IS EXPERIMENTAL. Please do not use. | |||
| */ | |||
| REG_OP(NonMaxSuppressionV6) | |||
| @@ -1729,3 +1723,4 @@ REG_OP(PSROIPoolingGradV2D) | |||
| } // namespace ge | |||
| #endif // OPS_BUILT_IN_OP_PROTO_INC_NN_DETECT_OPS_H_ | |||
+ 22
- 22
third_party/fwkacllib/inc/ops/nn_norm_ops.h
View File
| @@ -1073,26 +1073,6 @@ REG_OP(INInferV2D) | |||
| .OP_END_FACTORY_REG(INInferV2D) | |||
| /** | |||
| *@brief Performs instance normalization for inference of InHost part. | |||
| *@par Inputs:\n | |||
| * One input, including: (NC1HWC0 supported) | |||
| * variance: A [N, C1, 1, 1, C0] Tensor of type float32, for the variance. | |||
| *@par Attributes: | |||
| * epsilon: An optional float32, specifying the small value added to | |||
| variance to avoid dividing by zero. Defaults to "0.00001" . \n | |||
| *@par Outputs:\n | |||
| * variance_sqrt: A [N, C1, 1, 1, C0] Tensor of type float32, for the variance_sqrt. | |||
| */ | |||
| REG_OP(InHost) | |||
| .INPUT(variance, TensorType({DT_FLOAT})) | |||
| .OUTPUT(variance_sqrt, TensorType({DT_FLOAT})) | |||
| .ATTR(epsilon, Float, 0.00001) | |||
| .OP_END_FACTORY_REG(InHost) | |||
| /** | |||
| * @brief perform instance normalization to x. \n | |||
| * @par Inputs: | |||
| @@ -1124,6 +1104,26 @@ REG_OP(InstanceNorm) | |||
| .REQUIRED_ATTR(epsilon, Float) | |||
| .OP_END_FACTORY_REG(InstanceNorm) | |||
| /** | |||
| * @brief Computes Kl_div_loss_grad or Kl_div_loss_backward. \n | |||
| * @par Inputs: | |||
| * Three inputs, including: | |||
| * @li grad: A Tensor. Must be one of the following types: float16, float32. | |||
| * Required. | |||
| * @li input: A Tensor. Has the same type as "grad". Required. | |||
| * @li target: A Tensor. Has the same type as "grad". Required. \n | |||
| * @par Attributes: | |||
| * @li reduction: An optional attribute of type String. Defaults to "mean". \n | |||
| * @li log_target: An optional attribute of type Bool. Defaults to false. \n | |||
| * @par Outputs: | |||
| * @li y: A Tensor. Has the same type as "grad". \n | |||
| * @par Third-party framework compatibility | |||
| * Compatible with the Pytorch operator KlDivLossGrad. | |||
| */ | |||
| REG_OP(KlDivLossGrad) | |||
| .INPUT(grad, TensorType({DT_FLOAT16, DT_FLOAT})) | |||
| .INPUT(input, TensorType({DT_FLOAT16, DT_FLOAT})) | |||
| @@ -1453,12 +1453,12 @@ REG_OP(PoissonNllLoss) | |||
| * | |||
| * | |||
| * @par Output: | |||
| * y: A mutable Tensor of type int32, with the shape of [num_step, batch_size, hidden_size]. \n | |||
| * y: A mutable Tensor of type float16, with the shape of [num_step, batch_size, hidden_size]. \n | |||
| * | |||
| */ | |||
| REG_OP(RnnGenMask) | |||
| .INPUT(seq_length, TensorType({DT_INT32})) | |||
| .OUTPUT(seq_mask, TensorType({DT_INT32})) | |||
| .OUTPUT(seq_mask, TensorType({DT_FLOAT16})) | |||
| .REQUIRED_ATTR(num_step, Int) | |||
| .REQUIRED_ATTR(hidden_size, Int) | |||
| .OP_END_FACTORY_REG(RnnGenMask) | |||
+ 50
- 9
third_party/fwkacllib/inc/ops/nn_pooling_ops.h
View File
| @@ -237,18 +237,18 @@ REG_OP(AvgPool3DD) | |||
| * @li ceil_mode: When true, will use ceil instead of floor in the formula to compute the output shape. | |||
| * @li count_include_pad: When true, will include the zero-padding in the averaging calculation. | |||
| * @li divisor_override: if specified, it will be used as divisor, otherwise size of the pooling region will be used. | |||
| * @li data_format: A string, format of input data . | |||
| * @li data_format: A string, format of input data. | |||
| * @par Outputs: | |||
| * @output: A mutable tensor with the same shape and type as "orig_input". | |||
| * @output: A mutable tensor with the same shape and type as "orig_input_shape". | |||
| * @par Third-party framework compatibility | |||
| * @li Compatible with the TensorFlow operator AvgPoolGrad. | |||
| */ | |||
| REG_OP(AvgPool3DGrad) | |||
| .INPUT(orig_input_shape, TensorType({DT_FLOAT16, DT_FLOAT32, DT_DOUBLE})) | |||
| .INPUT(grads, TensorType({DT_INT32})) | |||
| .INPUT(orig_input_shape, TensorType({DT_INT32})) | |||
| .INPUT(grads, TensorType({DT_FLOAT16, DT_FLOAT32, DT_DOUBLE})) | |||
| .OUTPUT(output, TensorType({DT_FLOAT16, DT_FLOAT32, DT_DOUBLE})) | |||
| .REQUIRED_ATTR(ksize, ListInt) | |||
| .REQUIRED_ATTR(strides, ListInt) | |||
| @@ -888,7 +888,7 @@ REG_OP(AvgPoolV2Grad) | |||
| * @brief Computes gradients of averagev2 pooling function. | |||
| * @par Inputs: | |||
| * @li input_grad: An NHWC tensor of type float16, float32, or double. | |||
| *input_grad: An NHWC tensor of type float16, float32, or double. | |||
| * @par Attributes: | |||
| * @li orig_input_shape: A required tuple or list of type int32. | |||
| @@ -906,10 +906,10 @@ REG_OP(AvgPoolV2Grad) | |||
| * @li data_format: An optional string. Defaults to "NHWC". | |||
| * @par Outputs: | |||
| * @out_grad: A mutable tensor with the same shape and type as "orig_input". | |||
| *out_grad: A mutable tensor with the same shape and type as "orig_input". | |||
| * @par Third-party framework compatibility | |||
| * @li Compatible with the TensorFlow operator AvgPoolGrad. | |||
| *Compatible with the TensorFlow operator AvgPoolGrad. | |||
| */ | |||
| REG_OP(AvgPoolV2GradD) | |||
| .INPUT(input_grad, TensorType({DT_FLOAT16})) | |||
| @@ -1682,7 +1682,27 @@ REG_OP(MaxPoolWithArgmaxV1) | |||
| .ATTR(ceil_mode, Bool, false) | |||
| .OP_END_FACTORY_REG(MaxPoolWithArgmaxV1) | |||
| // SubSample | |||
| /** | |||
| *@brief Randomly sample a subset of positive and negative examples,and overwrite | |||
| the label vector to the ignore value (-1) for all elements that are not | |||
| included in the sample.\n | |||
| * @par Inputs: | |||
| * One input: | |||
| * labels: shape of labels,(N, ) label vector with values. \n | |||
| * @par Attributes: | |||
| * @li batch_size_per_images: A require attribute of type int. | |||
| * @li positive_fraction: A require attribute of type float. | |||
| *@par Outputs: | |||
| *y: The result of subSample. \n | |||
| *@par Third-party framework compatibility | |||
| *Compatible with the Pytorch operator SubSample. | |||
| *@par Restrictions: | |||
| *Warning: This operator can be integrated only by MaskRcnn. Please do not use it directly. | |||
| */ | |||
| REG_OP(SubSample) | |||
| .INPUT(labels, TensorType({DT_INT32})) | |||
| .OUTPUT(y, TensorType({DT_INT32})) | |||
| @@ -1690,7 +1710,28 @@ REG_OP(SubSample) | |||
| .REQUIRED_ATTR(positive_fraction, Float) | |||
| .OP_END_FACTORY_REG(SubSample) | |||
| // SubSampleLabels | |||
| /** | |||
| *@brief Randomly sample a subset of positive and negative examples,and overwrite | |||
| the label vector to the ignore value (-1) for all elements that are not | |||
| included in the sample.\n | |||
| * @par Inputs: | |||
| * two inputs, including: | |||
| * @li labels: shape of labels,(N, ) label vector with values:. | |||
| * @li shuffle_matrix: random matrix with shape (N, ). \n | |||
| * @par Attributes: | |||
| * @li batch_size_per_images: A require attribute of type int. | |||
| * @li positive_fraction: A require attribute of type float. | |||
| *@par Outputs: | |||
| *y: The result of subSample. \n | |||
| *@par Third-party framework compatibility | |||
| *Compatible with the Pytorch operator SubSampleLabels. | |||
| *@par Restrictions: | |||
| *Warning: This operator can be integrated only by MaskRcnn. Please do not use it directly. | |||
| */ | |||
| REG_OP(SubSampleLabels) | |||
| .INPUT(labels, TensorType({DT_INT32})) | |||
| .INPUT(shuffle_matrix, TensorType({DT_INT32})) | |||
+ 49
- 0
third_party/fwkacllib/inc/ops/nn_training_ops.h
View File
| @@ -2102,6 +2102,55 @@ REG_OP(FusedMulApplyMomentumExtern) | |||
| .OP_END_FACTORY_REG(FusedMulApplyMomentumExtern) | |||
| /** | |||
| *@brief Updates '*var' according to the momentum scheme. | |||
| * accum = accum * momentum - x1 * x2 * lr | |||
| * if use_nesterov is True: | |||
| * var += accum * momentum - x1 * x2 * lr | |||
| * else: | |||
| * var += accum | |||
| * | |||
| *@par Inputs: | |||
| *@li var: A mutable tensor. Must be one of the data types defined in | |||
| * TensorType::NumberType(). Should be from a Variable(). | |||
| *@li accum: A mutable tensor. Has the same type as "var". Should be from a | |||
| * Variable(). | |||
| *@li lr: A tensor for the learning rate. Has the same type as "var". Should be | |||
| * from a Variable(). | |||
| *@li x1: A Tensor has type TensorType::NumberType(). | |||
| *@li momentum: A scalar. Has the same type as "var". | |||
| *@li x2: A scalar has the same type as "var". | |||
| * | |||
| *@par Attributes: | |||
| *@li use_nesterov: An optional bool. Defaults to "False". | |||
| * If "True", var will be updated by using Nesterov momentum. | |||
| *@li use_locking: An optional bool. Defaults to "False". | |||
| * If "True", updating of the "var" tensor is protected by a lock; | |||
| * otherwise the behavior is undefined, but may exhibit less contention. | |||
| * | |||
| *@par Outputs: | |||
| * var: A mutable tensor. Has the same type as input "var". | |||
| * | |||
| *@attention Constraints: | |||
| * The input tensors must have the same shape. | |||
| * | |||
| *@par Third-party framework compatibility | |||
| * Compatible with the TensorFlow operator ResourceApplyKerasMomentum. | |||
| * | |||
| */ | |||
| REG_OP(FusedMulApplyKerasMomentum) | |||
| .INPUT(var, TensorType::NumberType()) | |||
| .INPUT(accum, TensorType::NumberType()) | |||
| .INPUT(lr, TensorType::NumberType()) | |||
| .INPUT(x1, TensorType::NumberType()) | |||
| .INPUT(momentum, TensorType::NumberType()) | |||
| .INPUT(x2, TensorType::NumberType()) | |||
| .OUTPUT(var, TensorType::NumberType()) | |||
| .OUTPUT(accum, TensorType::NumberType()) | |||
| .ATTR(use_locking, Bool, false) | |||
| .ATTR(use_nesterov, Bool, false) | |||
| .OP_END_FACTORY_REG(FusedMulApplyKerasMomentum) | |||
| /** | |||
| *@brief Update "g" according to the LARS algorithm . \n | |||
| *@par Inputs: | |||
+ 9
- 9
third_party/fwkacllib/inc/ops/parsing_ops.h
View File
| @@ -86,7 +86,7 @@ REG_OP(ParseSingleExample) | |||
| .ATTR(sparse_keys, ListString, {}) | |||
| .ATTR(dense_keys, ListString, {}) | |||
| .ATTR(sparse_types, ListType, {}) | |||
| .ATTR(dense_types, ListType, {}) | |||
| .ATTR(Tdense, ListType, {}) | |||
| .ATTR(dense_shapes, ListListInt, {}) | |||
| .OP_END_FACTORY_REG(ParseSingleExample) | |||
| @@ -173,9 +173,9 @@ REG_OP(ParseTensor) | |||
| REG_OP(DecodeCSV) | |||
| .INPUT(records, TensorType({DT_STRING})) | |||
| .DYNAMIC_INPUT(record_defaults, TensorType({DT_FLOAT, DT_DOUBLE, DT_INT32, | |||
| DT_INT64, DT_STRING, DT_RESOURCE})) | |||
| DT_INT64, DT_STRING})) | |||
| .DYNAMIC_OUTPUT(output, TensorType({DT_FLOAT, DT_DOUBLE, DT_INT32, | |||
| DT_INT64, DT_STRING, DT_RESOURCE})) | |||
| DT_INT64, DT_STRING})) | |||
| .ATTR(OUT_TYPE, ListType, {}) | |||
| .ATTR(field_delim, String, ",") | |||
| .ATTR(use_quote_delim, Bool, true) | |||
| @@ -283,12 +283,12 @@ REG_OP(ParseSingleSequenceExample) | |||
| .ATTR(Ncontext_dense, Int, 0) | |||
| .ATTR(Nfeature_list_sparse, Int, 0) | |||
| .ATTR(Nfeature_list_dense, Int, 0) | |||
| .REQUIRED_ATTR(context_sparse_types, ListType) | |||
| .REQUIRED_ATTR(Tcontext_dense, ListType) | |||
| .REQUIRED_ATTR(feature_list_dense_types, ListType) | |||
| .REQUIRED_ATTR(context_dense_shapes, ListListInt) | |||
| .REQUIRED_ATTR(feature_list_sparse_types, ListType) | |||
| .REQUIRED_ATTR(feature_list_dense_shapes, ListListInt) | |||
| .ATTR(context_sparse_types, ListType, {}) | |||
| .ATTR(Tcontext_dense, ListType, {}) | |||
| .ATTR(feature_list_dense_types, ListType, {}) | |||
| .ATTR(context_dense_shapes, ListListInt, {}) | |||
| .ATTR(feature_list_sparse_types, ListType, {}) | |||
| .ATTR(feature_list_dense_shapes, ListListInt, {}) | |||
| .OP_END_FACTORY_REG(ParseSingleSequenceExample) | |||
| } // namespace ge | |||
+ 2
- 0
third_party/fwkacllib/inc/ops/random_ops.h
View File
| @@ -548,6 +548,8 @@ REG_OP(ShuffleChannel) | |||
| * Each value along the axis zero represents the outcome of | |||
| * the corresponding sample in a batch. | |||
| * | |||
| * @par Restrictions: | |||
| * Warning:THIS FUNCTION IS EXPERIMENTAL. Please do not use. | |||
| */ | |||
| REG_OP(MultinomialFuss) | |||
| .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT, DT_FLOAT64})) | |||
+ 23
- 12
third_party/fwkacllib/inc/ops/rnn.h
View File
| @@ -190,7 +190,7 @@ REG_OP(DynamicRNNGrad) | |||
| *@li x:A required 4D Tensor. Must be one of the following types: float16, float32. The format must be FRACTAL_NZ. | |||
| *@li w:A required 4D Tensor. Must be one of the following types: float16, float32. The format must be FRACTAL_ZN_LSTM. | |||
| *@li b:A required 1D Tensor. Must be one of the following types: float16, float32. The format must be ND. | |||
| *@li seq_length:A optional 1D Tensor. Must be one of the following types: int32. The format must be ND. | |||
| *@li seq_length:A optional Tensor. Only Support float16 in FRACTAL_NZ and int32 in ND. | |||
| *@li init_h:A optional 4D Tensor. Must be one of the following types: float16, float32. The format must be FRACTAL_NZ. | |||
| *@li init_c:A optional 4D Tensor. Must be one of the following types: float16, float32. The format must be FRACTAL_NZ. | |||
| *@li wci:A 4D optional Tensor. Must be one of the following types: float16, float32. The format must be FRACTAL_ZN_LSTM. | |||
| @@ -228,7 +228,7 @@ REG_OP(DynamicRNN) | |||
| .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT})) | |||
| .INPUT(w, TensorType({DT_FLOAT16, DT_FLOAT})) | |||
| .INPUT(b, TensorType({DT_FLOAT16, DT_FLOAT})) | |||
| .OPTIONAL_INPUT(seq_length, TensorType({DT_INT32})) | |||
| .OPTIONAL_INPUT(seq_length, TensorType({DT_INT32, DT_FLOAT16})) | |||
| .OPTIONAL_INPUT(init_h, TensorType({DT_FLOAT16, DT_FLOAT})) | |||
| .OPTIONAL_INPUT(init_c, TensorType({DT_FLOAT16, DT_FLOAT})) | |||
| .OPTIONAL_INPUT(wci, TensorType({DT_FLOAT16, DT_FLOAT})) | |||
| @@ -698,9 +698,6 @@ REG_OP(DynamicGRU) | |||
| *@li reset:Must be one of the following types: float16, float32. The format must be FRACTAL_NZ. | |||
| *@li new:Must be one of the following types: float16, float32. The format must be FRACTAL_NZ. | |||
| *@li hidden_new:Must be one of the following types: float16, float32. The format must be FRACTAL_NZ. | |||
| *@par Restrictions: | |||
| *Warning: THIS FUNCTION IS EXPERIMENTAL. Please do not use. | |||
| */ | |||
| REG_OP(DynamicGRUV2) | |||
| .INPUT(x, TensorType({DT_FLOAT16})) | |||
| @@ -989,6 +986,27 @@ REG_OP(CommonLSTM) | |||
| .OP_END_FACTORY_REG(CommonLSTM) | |||
| /** | |||
| * @brief Calculate the mask. According to hidden_size and num_step, convert seq_length to mask. | |||
| * | |||
| * @par Inputs: | |||
| * @li seq_length: A 1D Tensor. Must be one of the following types: int32. Record the current length of each batch. [batch_size]. | |||
| * @li b: A 1D Tensor. Must be one of the following types: fp16/fp32. Record the hidden_size. [4 * hidden_size]. | |||
| * @li x: A 3D Tensor. Must be one of the following types: fp16/fp32. Record the num_step/batch_size/input_size. [num_step, batch_size, input_size]. | |||
| * | |||
| * @par Outputs: | |||
| * seq_mask: A 3D Tensor. Must be one of the following types: fp16/fp32. with the shape of [num_step, batch_size, hidden_size]. And has the same type as "b" \n | |||
| * | |||
| * @par Restrictions: | |||
| * Warning: THIS FUNCTION IS EXPERIMENTAL. Please do not use. | |||
| */ | |||
| REG_OP(RnnGenMaskV2) | |||
| .INPUT(seq_length, TensorType({DT_INT32})) | |||
| .INPUT(b, TensorType({{DT_FLOAT16, DT_FLOAT})) | |||
| .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT})) | |||
| .OUTPUT(seq_mask, TensorType({DT_FLOAT16, DT_FLOAT})) | |||
| .OP_END_FACTORY_REG(RnnGenMaskV2) | |||
| /** | |||
| * @brief Common GRU calculation. | |||
| * @par Inputs: | |||
| @@ -1002,22 +1020,15 @@ REG_OP(CommonLSTM) | |||
| * @par Attributes: | |||
| * @li activation_alpha: Optional scaling values used by some activation functions. \n | |||
| * @li activation_beta: Optional scaling values used by some activation functions. \n | |||
| * @li activations: A list of 2 (or 4 if bidirectional) activation functions for update, reset, and hidden gates. \n | |||
| * @li clip: Cell clip threshold. \n | |||
| * @li direction: Specify if the RNN is forward, reverse, or bidirectional. \n | |||
| * @li hidden_size: Number of neurons in the hidden layer. \n | |||
| * @li linear_before_reset: When computing the output of the hidden gate, apply the linear transformation before multiplying by the output of the reset gate. \n | |||
| * @par Outputs: | |||
| * @li y: A Tensor that concats all the intermediate output values of the hidden(float16,float32). The format must be FRACTAL_NZ | |||
| * @li y_h: The last output value of the hidden(float16,float32). The format must be FRACTAL_NZ | |||
| */ | |||
| REG_OP(CommonGRU) | |||
+ 27
- 0
third_party/fwkacllib/inc/ops/selection_ops.h
View File
| @@ -2254,6 +2254,33 @@ REG_OP(IndexFillD) | |||
| .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT, DT_INT32})) | |||
| .REQUIRED_ATTR(dim, Int) | |||
| .OP_END_FACTORY_REG(IndexFillD) | |||
| /** | |||
| * @brief For each row r of this and for each column c, do (*this)(r, c) += src(j, c), \n | |||
| * where j ranges from indexes[r].first through indexes[r].second - 1. \n | |||
| * In general indexes must be >= 0 and < src.NumRows(); \n | |||
| * but to represent an empty range you may use the pair (-1, -1) or any pair of numbers (i, j) such that i >= j. \n | |||
| * @par Inputs: | |||
| * Three inputs, including: | |||
| * @li x: A Tensor. Must be one of the following types: | |||
| * float16, float32. | |||
| * @li indices: A Tensor of the indices, type should be int32. | |||
| * @li src: A Tensor of the same type as "x". \n | |||
| * @par Outputs: | |||
| * @li x: A Tensor. Same as input "x". | |||
| * @par Third-party framework compatibility | |||
| * Compatible with the kaldi operator AddRowRanges. | |||
| */ | |||
| REG_OP(AddRowRanges) | |||
| .INPUT(x, TensorType({DT_FLOAT16,DT_FLOAT})) | |||
| .INPUT(src, TensorType({DT_FLOAT16,DT_FLOAT})) | |||
| .INPUT(indices, TensorType({DT_INT32})) | |||
| .OUTPUT(x, TensorType({DT_FLOAT16,DT_FLOAT})) | |||
| .OP_END_FACTORY_REG(AddRowRanges) | |||
| } // namespace ge | |||
| #endif // OPS_BUILT_IN_OP_PROTO_INC_SELECTION_OPS_H_ | |||
+ 2
- 0
third_party/fwkacllib/inc/ops/string_ops.h
View File
| @@ -114,6 +114,7 @@ REG_OP(UnicodeDecodeWithOffsets) | |||
| .ATTR(errors, String, "replace") | |||
| .ATTR(replacement_char, Int, 65533) | |||
| .ATTR(replace_control_characters, Bool, false) | |||
| .ATTR(Tsplits, Type, DT_INT64) | |||
| .OP_END_FACTORY_REG(UnicodeDecodeWithOffsets) | |||
| /** | |||
| @@ -161,6 +162,7 @@ REG_OP(UnicodeDecode) | |||
| .ATTR(errors, String, "replace") | |||
| .ATTR(replacement_char, Int, 65533) | |||
| .ATTR(replace_control_characters, Bool, false) | |||
| .ATTR(Tsplits, Type, DT_INT64) | |||
| .OP_END_FACTORY_REG(UnicodeDecode) | |||
| /** | |||
+ 5
- 25
third_party/fwkacllib/inc/toolchain/tuning_tool/tune_api.h
View File
| @@ -23,8 +23,8 @@ | |||
| * @attention 无 | |||
| * @param option [IN] 调优参数 | |||
| * @param msg [OUT] 调优异常下返回信息 | |||
| * @retval #MSTUNE_SUCCESS 执行成功 | |||
| * @retval #MSTUNE_FAILED 执行失败 | |||
| * @retval #AOE_SUCCESS 执行成功 | |||
| * @retval #AOE_FAILURE 执行失败 | |||
| * @par 依赖: | |||
| * @li tune_api.cpp：该接口所属的开发包。 | |||
| * @li tune_api.h：该接口声明所在的头文件。 | |||
| @@ -35,33 +35,13 @@ AoeStatus AoeOfflineTuning(const std::map<std::string, std::string> &option, std | |||
| /** | |||
| * @ingroup aoe | |||
| * @par 描述: 梯度调优 | |||
| * | |||
| * @attention 无 | |||
| * @param tuningGraph [IN] 调优图 | |||
| * @param dependGraph [IN] 调优依赖图 | |||
| * @param session [IN] ge连接会话 | |||
| * @param option [IN] 参数集. 包含调优参数及ge参数 | |||
| * @retval #MSTUNE_SUCCESS 执行成功 | |||
| * @retval #MSTUNE_FAILED 执行失败 | |||
| * @par 依赖: | |||
| * @li tune_api.cpp：该接口所属的开发包。 | |||
| * @li tune_api.h：该接口声明所在的头文件。 | |||
| * @see 无 | |||
| * @since | |||
| */ | |||
| extern "C" MsTuneStatus MsTrainTuning(ge::Graph &tuningGraph, std::vector<ge::Graph> &dependGraph, | |||
| ge::Session *session, const std::map<std::string, std::map<std::string, std::string>> &option); | |||
| /** | |||
| * @ingroup aoe | |||
| * @par 描述: 调优初始化 | |||
| * | |||
| * @attention 无 | |||
| * @param session [IN] ge连接会话 | |||
| * @param option [IN] 参数集. 包含调优参数及ge参数 | |||
| * @retval #AOE_SUCCESS 执行成功 | |||
| * @retval #AOE_FAILED 执行失败 | |||
| * @retval #AOE_FAILURE 执行失败 | |||
| * @par 依赖: | |||
| * @li tune_api.cpp：该接口所属的开发包。 | |||
| * @li tune_api.h：该接口声明所在的头文件。 | |||
| @@ -77,7 +57,7 @@ extern "C" AoeStatus AoeOnlineInitialize(ge::Session *session, const std::map<st | |||
| * @attention 无 | |||
| * @param 无 | |||
| * @retval #AOE_SUCCESS 执行成功 | |||
| * @retval #AOE_FAILED 执行失败 | |||
| * @retval #AOE_FAILURE 执行失败 | |||
| * @par 依赖: | |||
| * @li tune_api.cpp：该接口所属的开发包。 | |||
| * @li tune_api.h：该接口声明所在的头文件。 | |||
| @@ -96,7 +76,7 @@ extern "C" AoeStatus AoeOnlineFinalize(); | |||
| * @param session [IN] ge连接会话 | |||
| * @param option [IN] 参数集. 包含调优参数及ge参数 | |||
| * @retval #AOE_SUCCESS 执行成功 | |||
| * @retval #AOE_FAILED 执行失败 | |||
| * @retval #AOE_FAILURE 执行失败 | |||
| * @par 依赖: | |||
| * @li tune_api.cpp：该接口所属的开发包。 | |||
| * @li tune_api.h：该接口声明所在的头文件。 | |||