From 0f490f37d4b195e47376c2533607ef9d983568bb Mon Sep 17 00:00:00 2001 From: shenwei41 Date: Thu, 18 Mar 2021 22:16:17 +0800 Subject: [PATCH] update include headers --- inc/external/acl/acl.h | 8 +- inc/external/acl/ops/acl_dvpp.h | 425 +++++++++++------- third_party/fwkacllib/inc/ops/linalg_ops.h | 19 + third_party/fwkacllib/inc/ops/nn_detect_ops.h | 289 +++++++----- third_party/fwkacllib/inc/ops/nn_norm_ops.h | 25 ++ .../fwkacllib/inc/ops/nn_pooling_ops.h | 8 +- third_party/fwkacllib/inc/ops/pad_ops.h | 4 +- 7 files changed, 498 insertions(+), 280 deletions(-) diff --git a/inc/external/acl/acl.h b/inc/external/acl/acl.h index ef5b4772..eae87835 100644 --- a/inc/external/acl/acl.h +++ b/inc/external/acl/acl.h @@ -26,9 +26,9 @@ extern "C" { #endif // Current version is 1.0.0 -#define ACL_MAJOR_VERSION 1 -#define ACL_MINOR_VERSION 0 -#define ACL_PATCH_VERSION 0 +#define ACL_MAJOR_VERSION 1 +#define ACL_MINOR_VERSION 0 +#define ACL_PATCH_VERSION 0 /** * @ingroup AscendCL @@ -70,4 +70,4 @@ ACL_FUNC_VISIBILITY aclError aclrtGetVersion(int32_t *majorVersion, int32_t *min } #endif -#endif // INC_EXTERNAL_ACL_ACL_H_ +#endif // INC_EXTERNAL_ACL_ACL_H_ diff --git a/inc/external/acl/ops/acl_dvpp.h b/inc/external/acl/ops/acl_dvpp.h index dcaa3936..90dc70e8 100644 --- a/inc/external/acl/ops/acl_dvpp.h +++ b/inc/external/acl/ops/acl_dvpp.h @@ -53,109 +53,123 @@ typedef void (*aclvencCallback)(acldvppPicDesc *input, acldvppStreamDesc *output // Supported Pixel Format enum acldvppPixelFormat { - PIXEL_FORMAT_YUV_400 = 0, // 0 - PIXEL_FORMAT_YUV_SEMIPLANAR_420 = 1, // 1 - PIXEL_FORMAT_YVU_SEMIPLANAR_420 = 2, // 2 - PIXEL_FORMAT_YUV_SEMIPLANAR_422 = 3, // 3 - PIXEL_FORMAT_YVU_SEMIPLANAR_422 = 4, // 4 - PIXEL_FORMAT_YUV_SEMIPLANAR_444 = 5, // 5 - PIXEL_FORMAT_YVU_SEMIPLANAR_444 = 6, // 6 - PIXEL_FORMAT_YUYV_PACKED_422 = 7, // 7 - PIXEL_FORMAT_UYVY_PACKED_422 = 8, // 8 - PIXEL_FORMAT_YVYU_PACKED_422 = 9, // 9 - PIXEL_FORMAT_VYUY_PACKED_422 = 10, // 10 - PIXEL_FORMAT_YUV_PACKED_444 = 11, // 11 - PIXEL_FORMAT_RGB_888 = 12, // 12 - PIXEL_FORMAT_BGR_888 = 13, // 13 - PIXEL_FORMAT_ARGB_8888 = 14, // 14 - PIXEL_FORMAT_ABGR_8888 = 15, // 15 - PIXEL_FORMAT_RGBA_8888 = 16, // 16 - PIXEL_FORMAT_BGRA_8888 = 17, // 17 - PIXEL_FORMAT_YUV_SEMI_PLANNER_420_10BIT = 18, // 18 - PIXEL_FORMAT_YVU_SEMI_PLANNER_420_10BIT = 19, // 19 - PIXEL_FORMAT_YVU_PLANAR_420 = 20, // 20 - PIXEL_FORMAT_YVU_PLANAR_422, - PIXEL_FORMAT_YVU_PLANAR_444, - PIXEL_FORMAT_RGB_444 = 23, - PIXEL_FORMAT_BGR_444, - PIXEL_FORMAT_ARGB_4444, - PIXEL_FORMAT_ABGR_4444, - PIXEL_FORMAT_RGBA_4444, - PIXEL_FORMAT_BGRA_4444, - PIXEL_FORMAT_RGB_555, - PIXEL_FORMAT_BGR_555, - PIXEL_FORMAT_RGB_565, - PIXEL_FORMAT_BGR_565, - PIXEL_FORMAT_ARGB_1555, - PIXEL_FORMAT_ABGR_1555, - PIXEL_FORMAT_RGBA_1555, - PIXEL_FORMAT_BGRA_1555, - PIXEL_FORMAT_ARGB_8565, - PIXEL_FORMAT_ABGR_8565, - PIXEL_FORMAT_RGBA_8565, - PIXEL_FORMAT_BGRA_8565, - PIXEL_FORMAT_RGB_BAYER_8BPP = 50, - PIXEL_FORMAT_RGB_BAYER_10BPP, - PIXEL_FORMAT_RGB_BAYER_12BPP, - PIXEL_FORMAT_RGB_BAYER_14BPP, - PIXEL_FORMAT_RGB_BAYER_16BPP, - PIXEL_FORMAT_BGR_888_PLANAR = 70, - PIXEL_FORMAT_HSV_888_PACKAGE, - PIXEL_FORMAT_HSV_888_PLANAR, - PIXEL_FORMAT_LAB_888_PACKAGE, - PIXEL_FORMAT_LAB_888_PLANAR, - PIXEL_FORMAT_S8C1, - PIXEL_FORMAT_S8C2_PACKAGE, - PIXEL_FORMAT_S8C2_PLANAR, - PIXEL_FORMAT_S16C1, - PIXEL_FORMAT_U8C1, - PIXEL_FORMAT_U16C1, - PIXEL_FORMAT_S32C1, - PIXEL_FORMAT_U32C1, - PIXEL_FORMAT_U64C1, - PIXEL_FORMAT_S64C1, - PIXEL_FORMAT_YUV_SEMIPLANAR_440 = 1000, - PIXEL_FORMAT_YVU_SEMIPLANAR_440, - PIXEL_FORMAT_FLOAT32, - PIXEL_FORMAT_BUTT, - PIXEL_FORMAT_UNKNOWN = 10000 + PIXEL_FORMAT_YUV_400 = 0, // 0 + PIXEL_FORMAT_YUV_SEMIPLANAR_420 = 1, // 1 + PIXEL_FORMAT_YVU_SEMIPLANAR_420 = 2, // 2 + PIXEL_FORMAT_YUV_SEMIPLANAR_422 = 3, // 3 + PIXEL_FORMAT_YVU_SEMIPLANAR_422 = 4, // 4 + PIXEL_FORMAT_YUV_SEMIPLANAR_444 = 5, // 5 + PIXEL_FORMAT_YVU_SEMIPLANAR_444 = 6, // 6 + PIXEL_FORMAT_YUYV_PACKED_422 = 7, // 7 + PIXEL_FORMAT_UYVY_PACKED_422 = 8, // 8 + PIXEL_FORMAT_YVYU_PACKED_422 = 9, // 9 + PIXEL_FORMAT_VYUY_PACKED_422 = 10, // 10 + PIXEL_FORMAT_YUV_PACKED_444 = 11, // 11 + PIXEL_FORMAT_RGB_888 = 12, // 12 + PIXEL_FORMAT_BGR_888 = 13, // 13 + PIXEL_FORMAT_ARGB_8888 = 14, // 14 + PIXEL_FORMAT_ABGR_8888 = 15, // 15 + PIXEL_FORMAT_RGBA_8888 = 16, // 16 + PIXEL_FORMAT_BGRA_8888 = 17, // 17 + PIXEL_FORMAT_YUV_SEMI_PLANNER_420_10BIT = 18, // 18 + PIXEL_FORMAT_YVU_SEMI_PLANNER_420_10BIT = 19, // 19 + PIXEL_FORMAT_YVU_PLANAR_420 = 20, // 20 + PIXEL_FORMAT_YVU_PLANAR_422, + PIXEL_FORMAT_YVU_PLANAR_444, + PIXEL_FORMAT_RGB_444 = 23, + PIXEL_FORMAT_BGR_444, + PIXEL_FORMAT_ARGB_4444, + PIXEL_FORMAT_ABGR_4444, + PIXEL_FORMAT_RGBA_4444, + PIXEL_FORMAT_BGRA_4444, + PIXEL_FORMAT_RGB_555, + PIXEL_FORMAT_BGR_555, + PIXEL_FORMAT_RGB_565, + PIXEL_FORMAT_BGR_565, + PIXEL_FORMAT_ARGB_1555, + PIXEL_FORMAT_ABGR_1555, + PIXEL_FORMAT_RGBA_1555, + PIXEL_FORMAT_BGRA_1555, + PIXEL_FORMAT_ARGB_8565, + PIXEL_FORMAT_ABGR_8565, + PIXEL_FORMAT_RGBA_8565, + PIXEL_FORMAT_BGRA_8565, + PIXEL_FORMAT_RGB_BAYER_8BPP = 50, + PIXEL_FORMAT_RGB_BAYER_10BPP, + PIXEL_FORMAT_RGB_BAYER_12BPP, + PIXEL_FORMAT_RGB_BAYER_14BPP, + PIXEL_FORMAT_RGB_BAYER_16BPP, + PIXEL_FORMAT_BGR_888_PLANAR = 70, + PIXEL_FORMAT_HSV_888_PACKAGE, + PIXEL_FORMAT_HSV_888_PLANAR, + PIXEL_FORMAT_LAB_888_PACKAGE, + PIXEL_FORMAT_LAB_888_PLANAR, + PIXEL_FORMAT_S8C1, + PIXEL_FORMAT_S8C2_PACKAGE, + PIXEL_FORMAT_S8C2_PLANAR, + PIXEL_FORMAT_S16C1, + PIXEL_FORMAT_U8C1, + PIXEL_FORMAT_U16C1, + PIXEL_FORMAT_S32C1, + PIXEL_FORMAT_U32C1, + PIXEL_FORMAT_U64C1, + PIXEL_FORMAT_S64C1, + PIXEL_FORMAT_YUV_SEMIPLANAR_440 = 1000, + PIXEL_FORMAT_YVU_SEMIPLANAR_440, + PIXEL_FORMAT_FLOAT32, + PIXEL_FORMAT_BUTT, + PIXEL_FORMAT_UNKNOWN = 10000 }; // Stream Format -enum acldvppStreamFormat { H265_MAIN_LEVEL = 0, H264_BASELINE_LEVEL, H264_MAIN_LEVEL, H264_HIGH_LEVEL }; +enum acldvppStreamFormat { + H265_MAIN_LEVEL = 0, + H264_BASELINE_LEVEL, + H264_MAIN_LEVEL, + H264_HIGH_LEVEL +}; // Supported Channel Mode -enum acldvppChannelMode { DVPP_CHNMODE_VPC = 1, DVPP_CHNMODE_JPEGD = 2, DVPP_CHNMODE_JPEGE = 4 }; +enum acldvppChannelMode { + DVPP_CHNMODE_VPC = 1, + DVPP_CHNMODE_JPEGD = 2, + DVPP_CHNMODE_JPEGE = 4 +}; // Supported Border Type -enum acldvppBorderType { BORDER_CONSTANT = 0, BORDER_REPLICATE, BORDER_REFLECT, BORDER_REFLECT_101 }; +enum acldvppBorderType { + BORDER_CONSTANT = 0, + BORDER_REPLICATE, + BORDER_REFLECT, + BORDER_REFLECT_101 +}; // Venc parameter type enum aclvencChannelDescParamType { - ACL_VENC_THREAD_ID_UINT64 = 0, - ACL_VENC_CALLBACK_PTR, - ACL_VENC_PIXEL_FORMAT_UINT32, - ACL_VENC_ENCODE_TYPE_UINT32, - ACL_VENC_PIC_WIDTH_UINT32, - ACL_VENC_PIC_HEIGHT_UINT32, - ACL_VENC_KEY_FRAME_INTERVAL_UINT32, - ACL_VENC_BUF_ADDR_PTR, - ACL_VENC_BUF_SIZE_UINT32, - ACL_VENC_RC_MODE_UINT32, - ACL_VENC_SRC_RATE_UINT32, - ACL_VENC_MAX_BITRATE_UINT32, - ACL_VENC_MAX_IP_PROP_UINT32 + ACL_VENC_THREAD_ID_UINT64 = 0, + ACL_VENC_CALLBACK_PTR, + ACL_VENC_PIXEL_FORMAT_UINT32, + ACL_VENC_ENCODE_TYPE_UINT32, + ACL_VENC_PIC_WIDTH_UINT32, + ACL_VENC_PIC_HEIGHT_UINT32, + ACL_VENC_KEY_FRAME_INTERVAL_UINT32, + ACL_VENC_BUF_ADDR_PTR, + ACL_VENC_BUF_SIZE_UINT32, + ACL_VENC_RC_MODE_UINT32, + ACL_VENC_SRC_RATE_UINT32, + ACL_VENC_MAX_BITRATE_UINT32, + ACL_VENC_MAX_IP_PROP_UINT32 }; // Jpeg picture format enum acldvppJpegFormat { - ACL_JPEG_CSS_444 = 0, - ACL_JPEG_CSS_422, - ACL_JPEG_CSS_420, - ACL_JPEG_CSS_GRAY, - ACL_JPEG_CSS_440, - ACL_JPEG_CSS_411, - ACL_JPEG_CSS_UNKNOWN = 1000 + ACL_JPEG_CSS_444 = 0, + ACL_JPEG_CSS_422, + ACL_JPEG_CSS_420, + ACL_JPEG_CSS_GRAY, + ACL_JPEG_CSS_440, + ACL_JPEG_CSS_411, + ACL_JPEG_CSS_UNKNOWN = 1000 }; /** @@ -509,7 +523,9 @@ ACL_FUNC_VISIBILITY uint32_t acldvppGetPicDescRetCode(const acldvppPicDesc *picD * @retval null for failed. * @retval other success */ -ACL_FUNC_VISIBILITY acldvppRoiConfig *acldvppCreateRoiConfig(uint32_t left, uint32_t right, uint32_t top, +ACL_FUNC_VISIBILITY acldvppRoiConfig *acldvppCreateRoiConfig(uint32_t left, + uint32_t right, + uint32_t top, uint32_t bottom); /** @@ -588,7 +604,10 @@ ACL_FUNC_VISIBILITY aclError acldvppSetRoiConfigBottom(acldvppRoiConfig *config, * @retval ACL_SUCCESS The function is successfully executed. * @retval OtherValues Failure */ -ACL_FUNC_VISIBILITY aclError acldvppSetRoiConfig(acldvppRoiConfig *config, uint32_t left, uint32_t right, uint32_t top, +ACL_FUNC_VISIBILITY aclError acldvppSetRoiConfig(acldvppRoiConfig *config, + uint32_t left, + uint32_t right, + uint32_t top, uint32_t bottom); /** @@ -1077,8 +1096,7 @@ ACL_FUNC_VISIBILITY aclError aclvencSetChannelDescMaxBitRate(aclvencChannelDesc * @retval ACL_SUCCESS for success, other for failure */ ACL_FUNC_VISIBILITY aclError aclvencSetChannelDescParam(aclvencChannelDesc *channelDesc, - aclvencChannelDescParamType paramType, size_t length, - const void *param); + aclvencChannelDescParamType paramType, size_t length, const void *param); /** * @ingroup AscendCL @@ -1227,8 +1245,7 @@ ACL_FUNC_VISIBILITY uint32_t aclvencGetChannelDescMaxBitRate(const aclvencChanne * @retval ACL_SUCCESS for success, other for failure */ ACL_FUNC_VISIBILITY aclError aclvencGetChannelDescParam(const aclvencChannelDesc *channelDesc, - aclvencChannelDescParamType paramType, size_t length, - size_t *paramRetSize, void *param); + aclvencChannelDescParamType paramType, size_t length, size_t *paramRetSize, void *param); /** * @ingroup AscendCL @@ -1528,7 +1545,10 @@ ACL_FUNC_VISIBILITY aclError aclvdecDestroyFrameConfig(aclvdecFrameConfig *vdecF * @retval ACL_SUCCESS The function is successfully executed. * @retval OtherValues Failure */ -ACL_FUNC_VISIBILITY aclError acldvppJpegGetImageInfo(const void *data, uint32_t size, uint32_t *width, uint32_t *height, +ACL_FUNC_VISIBILITY aclError acldvppJpegGetImageInfo(const void *data, + uint32_t size, + uint32_t *width, + uint32_t *height, int32_t *components); /** @@ -1545,8 +1565,11 @@ ACL_FUNC_VISIBILITY aclError acldvppJpegGetImageInfo(const void *data, uint32_t * @retval ACL_SUCCESS The function is successfully executed. * @retval OtherValues Failure */ -ACL_FUNC_VISIBILITY aclError acldvppJpegGetImageInfoV2(const void *data, uint32_t size, uint32_t *width, - uint32_t *height, int32_t *components, +ACL_FUNC_VISIBILITY aclError acldvppJpegGetImageInfoV2(const void *data, + uint32_t size, + uint32_t *width, + uint32_t *height, + int32_t *components, acldvppJpegFormat *format); /** @@ -1561,7 +1584,8 @@ ACL_FUNC_VISIBILITY aclError acldvppJpegGetImageInfoV2(const void *data, uint32_ * @retval OtherValues Failure */ ACL_FUNC_VISIBILITY aclError acldvppJpegPredictEncSize(const acldvppPicDesc *inputDesc, - const acldvppJpegeConfig *config, uint32_t *size); + const acldvppJpegeConfig *config, + uint32_t *size); /** * @ingroup AscendCL @@ -1575,8 +1599,10 @@ ACL_FUNC_VISIBILITY aclError acldvppJpegPredictEncSize(const acldvppPicDesc *inp * @retval ACL_SUCCESS The function is successfully executed. * @retval OtherValues Failure */ -ACL_FUNC_VISIBILITY aclError acldvppJpegPredictDecSize(const void *data, uint32_t dataSize, - acldvppPixelFormat outputPixelFormat, uint32_t *decSize); +ACL_FUNC_VISIBILITY aclError acldvppJpegPredictDecSize(const void *data, + uint32_t dataSize, + acldvppPixelFormat outputPixelFormat, + uint32_t *decSize); /** * @ingroup AscendCL @@ -1591,8 +1617,11 @@ ACL_FUNC_VISIBILITY aclError acldvppJpegPredictDecSize(const void *data, uint32_ * @retval ACL_SUCCESS The function is successfully executed. * @retval OtherValues Failure */ -ACL_FUNC_VISIBILITY aclError acldvppPngGetImageInfo(const void *data, uint32_t dataSize, uint32_t *width, - uint32_t *height, int32_t *components); +ACL_FUNC_VISIBILITY aclError acldvppPngGetImageInfo(const void *data, + uint32_t dataSize, + uint32_t *width, + uint32_t *height, + int32_t *components); /** * @ingroup AscendCL @@ -1606,8 +1635,10 @@ ACL_FUNC_VISIBILITY aclError acldvppPngGetImageInfo(const void *data, uint32_t d * @retval ACL_SUCCESS The function is successfully executed. * @retval OtherValues Failure */ -ACL_FUNC_VISIBILITY aclError acldvppPngPredictDecSize(const void *data, uint32_t dataSize, - acldvppPixelFormat outputPixelFormat, uint32_t *decSize); +ACL_FUNC_VISIBILITY aclError acldvppPngPredictDecSize(const void *data, + uint32_t dataSize, + acldvppPixelFormat outputPixelFormat, + uint32_t *decSize); /** * @ingroup AscendCL @@ -1671,8 +1702,10 @@ ACL_FUNC_VISIBILITY aclError acldvppDestroyChannel(acldvppChannelDesc *channelDe * @see acldvppCreateChannel | acldvppCreatePicDesc * | acldvppCreateResizeConfig */ -ACL_FUNC_VISIBILITY aclError acldvppVpcResizeAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, - acldvppPicDesc *outputDesc, acldvppResizeConfig *resizeConfig, +ACL_FUNC_VISIBILITY aclError acldvppVpcResizeAsync(acldvppChannelDesc *channelDesc, + acldvppPicDesc *inputDesc, + acldvppPicDesc *outputDesc, + acldvppResizeConfig *resizeConfig, aclrtStream stream); /** @@ -1708,8 +1741,10 @@ ACL_FUNC_VISIBILITY aclError acldvppVpcResizeAsync(acldvppChannelDesc *channelDe * @retval ACL_SUCCESS The function is successfully executed. * @retval OtherValues Failure */ -ACL_FUNC_VISIBILITY aclError acldvppVpcCropAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, - acldvppPicDesc *outputDesc, acldvppRoiConfig *cropArea, +ACL_FUNC_VISIBILITY aclError acldvppVpcCropAsync(acldvppChannelDesc *channelDesc, + acldvppPicDesc *inputDesc, + acldvppPicDesc *outputDesc, + acldvppRoiConfig *cropArea, aclrtStream stream); /** @@ -1746,9 +1781,13 @@ ACL_FUNC_VISIBILITY aclError acldvppVpcCropAsync(acldvppChannelDesc *channelDesc * @retval ACL_SUCCESS The function is successfully executed. * @retval OtherValues Failure */ -ACL_FUNC_VISIBILITY aclError acldvppVpcCropResizeAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, - acldvppPicDesc *outputDesc, acldvppRoiConfig *cropArea, - acldvppResizeConfig *resizeConfig, aclrtStream stream); +ACL_FUNC_VISIBILITY aclError acldvppVpcCropResizeAsync(acldvppChannelDesc *channelDesc, + acldvppPicDesc *inputDesc, + acldvppPicDesc *outputDesc, + acldvppRoiConfig *cropArea, + acldvppResizeConfig *resizeConfig, + aclrtStream stream); + /** * @ingroup AscendCL @@ -1772,9 +1811,12 @@ ACL_FUNC_VISIBILITY aclError acldvppVpcCropResizeAsync(acldvppChannelDesc *chann * @see acldvppCreateChannel | acldvppCreateBatchPicDesc | acldvppCreateRoiConfig */ ACL_FUNC_VISIBILITY aclError acldvppVpcBatchCropAsync(acldvppChannelDesc *channelDesc, - acldvppBatchPicDesc *srcBatchPicDescs, uint32_t *roiNums, - uint32_t size, acldvppBatchPicDesc *dstBatchPicDescs, - acldvppRoiConfig *cropAreas[], aclrtStream stream); + acldvppBatchPicDesc *srcBatchPicDescs, + uint32_t *roiNums, + uint32_t size, + acldvppBatchPicDesc *dstBatchPicDescs, + acldvppRoiConfig *cropAreas[], + aclrtStream stream); /** * @ingroup AscendCL @@ -1799,10 +1841,13 @@ ACL_FUNC_VISIBILITY aclError acldvppVpcBatchCropAsync(acldvppChannelDesc *channe * @see acldvppCreateChannel | acldvppCreateBatchPicDesc | acldvppCreateRoiConfig | acldvppCreateDvppConfig */ ACL_FUNC_VISIBILITY aclError acldvppVpcBatchCropResizeAsync(acldvppChannelDesc *channelDesc, - acldvppBatchPicDesc *srcBatchPicDescs, uint32_t *roiNums, - uint32_t size, acldvppBatchPicDesc *dstBatchPicDescs, + acldvppBatchPicDesc *srcBatchPicDescs, + uint32_t *roiNums, + uint32_t size, + acldvppBatchPicDesc *dstBatchPicDescs, acldvppRoiConfig *cropAreas[], - acldvppResizeConfig *resizeConfig, aclrtStream stream); + acldvppResizeConfig *resizeConfig, + aclrtStream stream); /** * @ingroup AscendCL @@ -1825,9 +1870,12 @@ ACL_FUNC_VISIBILITY aclError acldvppVpcBatchCropResizeAsync(acldvppChannelDesc * * * @see acldvppCreateChannel | acldvppCreatePicDesc | acldvppCreateRoiConfig */ -ACL_FUNC_VISIBILITY aclError acldvppVpcCropAndPasteAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, - acldvppPicDesc *outputDesc, acldvppRoiConfig *cropArea, - acldvppRoiConfig *pasteArea, aclrtStream stream); +ACL_FUNC_VISIBILITY aclError acldvppVpcCropAndPasteAsync(acldvppChannelDesc *channelDesc, + acldvppPicDesc *inputDesc, + acldvppPicDesc *outputDesc, + acldvppRoiConfig *cropArea, + acldvppRoiConfig *pasteArea, + aclrtStream stream); /** * @ingroup AscendCL @@ -1851,10 +1899,13 @@ ACL_FUNC_VISIBILITY aclError acldvppVpcCropAndPasteAsync(acldvppChannelDesc *cha * * @see acldvppCreateChannel | acldvppCreatePicDesc | acldvppCreateRoiConfig | acldvppCreateResizeConfig */ -ACL_FUNC_VISIBILITY aclError acldvppVpcCropResizePasteAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, - acldvppPicDesc *outputDesc, acldvppRoiConfig *cropArea, +ACL_FUNC_VISIBILITY aclError acldvppVpcCropResizePasteAsync(acldvppChannelDesc *channelDesc, + acldvppPicDesc *inputDesc, + acldvppPicDesc *outputDesc, + acldvppRoiConfig *cropArea, acldvppRoiConfig *pasteArea, - acldvppResizeConfig *resizeConfig, aclrtStream stream); + acldvppResizeConfig *resizeConfig, + aclrtStream stream); /** * @ingroup AscendCL @@ -1879,11 +1930,14 @@ ACL_FUNC_VISIBILITY aclError acldvppVpcCropResizePasteAsync(acldvppChannelDesc * * * @see acldvppCreateChannel | acldvppCreateBatchPicDesc | acldvppCreateRoiConfig */ -ACL_FUNC_VISIBILITY aclError acldvppVpcBatchCropAndPasteAsync(acldvppChannelDesc *channelDesc, - acldvppBatchPicDesc *srcBatchPicDescs, uint32_t *roiNums, - uint32_t size, acldvppBatchPicDesc *dstBatchPicDescs, - acldvppRoiConfig *cropAreas[], - acldvppRoiConfig *pasteAreas[], aclrtStream stream); + ACL_FUNC_VISIBILITY aclError acldvppVpcBatchCropAndPasteAsync(acldvppChannelDesc *channelDesc, + acldvppBatchPicDesc *srcBatchPicDescs, + uint32_t *roiNums, + uint32_t size, + acldvppBatchPicDesc *dstBatchPicDescs, + acldvppRoiConfig *cropAreas[], + acldvppRoiConfig *pasteAreas[], + aclrtStream stream); /** * @ingroup AscendCL @@ -1909,10 +1963,16 @@ ACL_FUNC_VISIBILITY aclError acldvppVpcBatchCropAndPasteAsync(acldvppChannelDesc * * @see acldvppCreateChannel | acldvppCreateBatchPicDesc | acldvppCreateRoiConfig | acldvppCreateResizeConfig */ -ACL_FUNC_VISIBILITY aclError acldvppVpcBatchCropResizePasteAsync( - acldvppChannelDesc *channelDesc, acldvppBatchPicDesc *srcBatchPicDescs, uint32_t *roiNums, uint32_t size, - acldvppBatchPicDesc *dstBatchPicDescs, acldvppRoiConfig *cropAreas[], acldvppRoiConfig *pasteAreas[], - acldvppResizeConfig *resizeConfig, aclrtStream stream); +ACL_FUNC_VISIBILITY aclError acldvppVpcBatchCropResizePasteAsync(acldvppChannelDesc *channelDesc, + acldvppBatchPicDesc *srcBatchPicDescs, + uint32_t *roiNums, + uint32_t size, + acldvppBatchPicDesc *dstBatchPicDescs, + acldvppRoiConfig *cropAreas[], + acldvppRoiConfig *pasteAreas[], + acldvppResizeConfig *resizeConfig, + aclrtStream stream); + /** * @ingroup AscendCL @@ -1940,8 +2000,11 @@ ACL_FUNC_VISIBILITY aclError acldvppVpcBatchCropResizePasteAsync( * * @see acldvppCreateChannel | acldvppCreatePicDesc */ -ACL_FUNC_VISIBILITY aclError acldvppJpegDecodeAsync(acldvppChannelDesc *channelDesc, const void *data, uint32_t size, - acldvppPicDesc *outputDesc, aclrtStream stream); +ACL_FUNC_VISIBILITY aclError acldvppJpegDecodeAsync(acldvppChannelDesc *channelDesc, + const void *data, + uint32_t size, + acldvppPicDesc *outputDesc, + aclrtStream stream); /** * @ingroup AscendCL @@ -1959,8 +2022,11 @@ ACL_FUNC_VISIBILITY aclError acldvppJpegDecodeAsync(acldvppChannelDesc *channelD * * @see acldvppCreateChannel | acldvppCreateJpegeConfig */ -ACL_FUNC_VISIBILITY aclError acldvppJpegEncodeAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, - const void *data, uint32_t *size, acldvppJpegeConfig *config, +ACL_FUNC_VISIBILITY aclError acldvppJpegEncodeAsync(acldvppChannelDesc *channelDesc, + acldvppPicDesc *inputDesc, + const void *data, + uint32_t *size, + acldvppJpegeConfig *config, aclrtStream stream); /** @@ -1978,8 +2044,11 @@ ACL_FUNC_VISIBILITY aclError acldvppJpegEncodeAsync(acldvppChannelDesc *channelD * * @see acldvppCreateChannel | acldvppCreatePicDesc */ -ACL_FUNC_VISIBILITY aclError acldvppPngDecodeAsync(acldvppChannelDesc *channelDesc, const void *data, uint32_t size, - acldvppPicDesc *outputDesc, aclrtStream stream); +ACL_FUNC_VISIBILITY aclError acldvppPngDecodeAsync(acldvppChannelDesc *channelDesc, + const void *data, + uint32_t size, + acldvppPicDesc *outputDesc, + aclrtStream stream); /** * @ingroup AscendCL @@ -2034,8 +2103,11 @@ ACL_FUNC_VISIBILITY aclError aclvdecDestroyChannel(aclvdecChannelDesc *channelDe * * @see aclvdecCreateChannel | acldvppCreateStreamDesc | acldvppCreatePicDesc */ -ACL_FUNC_VISIBILITY aclError aclvdecSendFrame(aclvdecChannelDesc *channelDesc, acldvppStreamDesc *input, - acldvppPicDesc *output, aclvdecFrameConfig *config, void *userData); +ACL_FUNC_VISIBILITY aclError aclvdecSendFrame(aclvdecChannelDesc *channelDesc, + acldvppStreamDesc *input, + acldvppPicDesc *output, + aclvdecFrameConfig *config, + void *userData); /** * @ingroup AscendCL @@ -2054,8 +2126,10 @@ ACL_FUNC_VISIBILITY aclError aclvdecSendFrame(aclvdecChannelDesc *channelDesc, a * * @see aclvdecCreateChannel | acldvppCreateStreamDesc | acldvppCreatePicDesc | aclvdecSendFrame */ -ACL_FUNC_VISIBILITY aclError aclvdecSendSkippedFrame(aclvdecChannelDesc *channelDesc, acldvppStreamDesc *input, - aclvdecFrameConfig *config, void *userData); +ACL_FUNC_VISIBILITY aclError aclvdecSendSkippedFrame(aclvdecChannelDesc *channelDesc, + acldvppStreamDesc *input, + aclvdecFrameConfig *config, + void *userData); /** * @ingroup AscendCL @@ -2076,8 +2150,10 @@ ACL_FUNC_VISIBILITY aclError aclvdecSendSkippedFrame(aclvdecChannelDesc *channel * * @see acldvppCreateChannel | acldvppCreatePicDesc */ -ACL_FUNC_VISIBILITY aclError acldvppVpcConvertColorAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, - acldvppPicDesc *outputDesc, aclrtStream stream); +ACL_FUNC_VISIBILITY aclError acldvppVpcConvertColorAsync(acldvppChannelDesc *channelDesc, + acldvppPicDesc *inputDesc, + acldvppPicDesc *outputDesc, + aclrtStream stream); /** * @ingroup AscendCL @@ -2099,8 +2175,11 @@ ACL_FUNC_VISIBILITY aclError acldvppVpcConvertColorAsync(acldvppChannelDesc *cha * * @see acldvppCreateChannel | acldvppCreatePicDesc */ -ACL_FUNC_VISIBILITY aclError acldvppVpcPyrDownAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, - acldvppPicDesc *outputDesc, void *reserve, aclrtStream stream); +ACL_FUNC_VISIBILITY aclError acldvppVpcPyrDownAsync(acldvppChannelDesc *channelDesc, + acldvppPicDesc *inputDesc, + acldvppPicDesc *outputDesc, + void *reserve, + aclrtStream stream); /** * @ingroup AscendCL @@ -2112,7 +2191,8 @@ ACL_FUNC_VISIBILITY aclError acldvppVpcPyrDownAsync(acldvppChannelDesc *channelD * @retval ACL_SUCCESS The function is successfully executed. * @retval OtherValues Failure */ -ACL_FUNC_VISIBILITY aclError acldvppSetChannelDescMode(acldvppChannelDesc *channelDesc, uint32_t mode); +ACL_FUNC_VISIBILITY aclError acldvppSetChannelDescMode(acldvppChannelDesc *channelDesc, + uint32_t mode); /** * @ingroup AscendCL @@ -2147,7 +2227,8 @@ ACL_FUNC_VISIBILITY uint32_t acldvppGetResizeConfigInterpolation(const acldvppRe * @retval ACL_SUCCESS The function is successfully executed. * @retval OtherValues Failure */ -ACL_FUNC_VISIBILITY aclError aclvdecSetChannelDescOutMode(aclvdecChannelDesc *channelDesc, uint32_t outMode); +ACL_FUNC_VISIBILITY aclError aclvdecSetChannelDescOutMode(aclvdecChannelDesc *channelDesc, + uint32_t outMode); /** * @ingroup AscendCL @@ -2244,7 +2325,9 @@ ACL_FUNC_VISIBILITY uint32_t acldvppGetLutMapDims(const acldvppLutMap *lutMap); * @retval ACL_SUCCESS The function is successfully executed. * @retval OtherValues Failure */ -ACL_FUNC_VISIBILITY aclError acldvppGetLutMapData(const acldvppLutMap *lutMap, uint32_t dim, uint8_t **data, +ACL_FUNC_VISIBILITY aclError acldvppGetLutMapData(const acldvppLutMap *lutMap, + uint32_t dim, + uint8_t **data, uint32_t *len); /** * @ingroup AscendCL @@ -2262,8 +2345,10 @@ ACL_FUNC_VISIBILITY aclError acldvppGetLutMapData(const acldvppLutMap *lutMap, u * @see acldvppCreateChannel|acldvppCreatePicDesc|acldvppCreateLutMap */ ACL_FUNC_VISIBILITY aclError acldvppVpcEqualizeHistAsync(const acldvppChannelDesc *channelDesc, - const acldvppPicDesc *inputDesc, acldvppPicDesc *outputDesc, - const acldvppLutMap *lutMap, aclrtStream stream); + const acldvppPicDesc *inputDesc, + acldvppPicDesc *outputDesc, + const acldvppLutMap *lutMap, + aclrtStream stream); /** * @ingroup AscendCL @@ -2284,7 +2369,8 @@ ACL_FUNC_VISIBILITY acldvppBorderConfig *acldvppCreateBorderConfig(); * * @retval ACL_SUCCESS for success, other for failure */ -ACL_FUNC_VISIBILITY aclError acldvppSetBorderConfigValue(acldvppBorderConfig *borderConfig, uint32_t index, +ACL_FUNC_VISIBILITY aclError acldvppSetBorderConfigValue(acldvppBorderConfig *borderConfig, + uint32_t index, double value); /** @@ -2429,8 +2515,10 @@ ACL_FUNC_VISIBILITY aclError acldvppDestroyBorderConfig(acldvppBorderConfig *bor * @see acldvppCreateChannel|acldvppCreatePicDesc|acldvppCreateBorderConfig */ ACL_FUNC_VISIBILITY aclError acldvppVpcMakeBorderAsync(const acldvppChannelDesc *channelDesc, - const acldvppPicDesc *inputDesc, acldvppPicDesc *outputDesc, - const acldvppBorderConfig *borderConfig, aclrtStream stream); + const acldvppPicDesc *inputDesc, + acldvppPicDesc *outputDesc, + const acldvppBorderConfig *borderConfig, + aclrtStream stream); /** * @ingroup AscendCL @@ -2447,8 +2535,11 @@ ACL_FUNC_VISIBILITY aclError acldvppVpcMakeBorderAsync(const acldvppChannelDesc * * @see acldvppCreateChannel | acldvppCreatePicDesc | acldvppCreateHist */ -ACL_FUNC_VISIBILITY aclError acldvppVpcCalcHistAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *srcPicDesc, - acldvppHist *hist, void *reserve, aclrtStream stream); +ACL_FUNC_VISIBILITY aclError acldvppVpcCalcHistAsync(acldvppChannelDesc *channelDesc, + acldvppPicDesc *srcPicDesc, + acldvppHist *hist, + void *reserve, + aclrtStream stream); /** * @ingroup AscendCL @@ -2457,7 +2548,7 @@ ACL_FUNC_VISIBILITY aclError acldvppVpcCalcHistAsync(acldvppChannelDesc *channel * @retval null for failed. * @retval OtherValues success. */ -ACL_FUNC_VISIBILITY acldvppHist *acldvppCreateHist(); +ACL_FUNC_VISIBILITY acldvppHist* acldvppCreateHist(); /** * @ingroup AscendCL @@ -2514,7 +2605,7 @@ ACL_FUNC_VISIBILITY aclError acldvppGetHistData(acldvppHist *hist, uint32_t dim, * * @see acldvppCreateHist | acldvppVpcCalcHistAsync */ -ACL_FUNC_VISIBILITY uint32_t acldvppGetHistRetCode(acldvppHist *hist); +ACL_FUNC_VISIBILITY uint32_t acldvppGetHistRetCode(acldvppHist* hist); /** * @ingroup AscendCL @@ -2533,6 +2624,7 @@ ACL_FUNC_VISIBILITY uint32_t acldvppGetHistRetCode(acldvppHist *hist); */ ACL_FUNC_VISIBILITY aclError acldvppClearHist(acldvppHist *hist); + /** * @ingroup AscendCL * @brief dvpp vpc batch crop, resize config and make border. @@ -2556,13 +2648,18 @@ ACL_FUNC_VISIBILITY aclError acldvppClearHist(acldvppHist *hist); * * @see acldvppCreateChannel | acldvppCreateBatchPicDesc | acldvppCreateRoiConfig | acldvppCreateResizeConfig */ -ACL_FUNC_VISIBILITY aclError acldvppVpcBatchCropResizeMakeBorderAsync( - acldvppChannelDesc *channelDesc, acldvppBatchPicDesc *srcBatchPicDescs, uint32_t *roiNums, uint32_t size, - acldvppBatchPicDesc *dstBatchPicDescs, acldvppRoiConfig *cropAreas[], acldvppBorderConfig *borderCfgs[], - acldvppResizeConfig *resizeConfig, aclrtStream stream); +ACL_FUNC_VISIBILITY aclError acldvppVpcBatchCropResizeMakeBorderAsync(acldvppChannelDesc *channelDesc, + acldvppBatchPicDesc *srcBatchPicDescs, + uint32_t *roiNums, + uint32_t size, + acldvppBatchPicDesc *dstBatchPicDescs, + acldvppRoiConfig *cropAreas[], + acldvppBorderConfig *borderCfgs[], + acldvppResizeConfig *resizeConfig, + aclrtStream stream); #ifdef __cplusplus } #endif -#endif // INC_EXTERNAL_ACL_OPS_ACL_DVPP_H_ +#endif // INC_EXTERNAL_ACL_OPS_ACL_DVPP_H_ diff --git a/third_party/fwkacllib/inc/ops/linalg_ops.h b/third_party/fwkacllib/inc/ops/linalg_ops.h index 1a59d88e..a334570c 100644 --- a/third_party/fwkacllib/inc/ops/linalg_ops.h +++ b/third_party/fwkacllib/inc/ops/linalg_ops.h @@ -82,6 +82,25 @@ REG_OP(Cholesky) DT_FLOAT16, DT_COMPLEX64, DT_COMPLEX128})) .OP_END_FACTORY_REG(Cholesky) +/** +*@brief Computes the outer product of two 1D vectors . \n + +*@par Inputs: +*The input x and vec2 has to be a 1D vector.Inputs include: +*@li x:A Tensor. Must be one of the following types: float16, float32. +Shape is [N] . \n +*@li vec2:A Tensor. Must have the same type as x. Shape is [M] . \n + +*@par Outputs: +*y:A Tensor. Has the same type as x . \n +*/ + +REG_OP(Ger) + .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(vec2, TensorType({DT_FLOAT16, DT_FLOAT})) + .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT})) + .OP_END_FACTORY_REG(Ger) + /** *@brief Computes the sign and the log of the absolute value of the determinant of one or more square matrices . \n diff --git a/third_party/fwkacllib/inc/ops/nn_detect_ops.h b/third_party/fwkacllib/inc/ops/nn_detect_ops.h index af59b4e2..33148e62 100644 --- a/third_party/fwkacllib/inc/ops/nn_detect_ops.h +++ b/third_party/fwkacllib/inc/ops/nn_detect_ops.h @@ -254,22 +254,22 @@ is min_size/sqrt(aspect_ratio), the width is min_size*sqrt(aspect_ratio). Defaul *@par Third-party framework compatibility * It is a custom operator. It has no corresponding operator in Caffe. */ - REG_OP(PriorBox) - .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT})) - .INPUT(img, TensorType({DT_FLOAT16, DT_FLOAT})) - .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT})) - .REQUIRED_ATTR(min_size, ListFloat) - .REQUIRED_ATTR(max_size, ListFloat) - .REQUIRED_ATTR(aspect_ratio, ListFloat) - .ATTR(img_h, Int, 0) - .ATTR(img_w, Int, 0) - .ATTR(step_h, Float, 0.0) - .ATTR(step_w, Float, 0.0) - .ATTR(flip, Bool, true) - .ATTR(clip, Bool, false) - .ATTR(offset, Float, 0.5) - .ATTR(variance, ListFloat, {0.1}) - .OP_END_FACTORY_REG(PriorBox); +REG_OP(PriorBox) + .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(img, TensorType({DT_FLOAT16, DT_FLOAT})) + .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT})) + .REQUIRED_ATTR(min_size, ListFloat) + .REQUIRED_ATTR(max_size, ListFloat) + .REQUIRED_ATTR(aspect_ratio, ListFloat) + .ATTR(img_h, Int, 0) + .ATTR(img_w, Int, 0) + .ATTR(step_h, Float, 0.0) + .ATTR(step_w, Float, 0.0) + .ATTR(flip, Bool, true) + .ATTR(clip, Bool, false) + .ATTR(offset, Float, 0.5) + .ATTR(variance, ListFloat, {0.1}) + .OP_END_FACTORY_REG(PriorBox); /** *@brief Performs SSD prior box detection, with four additional matrices and the "aspect_ratio" attribute deleted compared to PriorBox . \n @@ -306,25 +306,25 @@ is min_size/sqrt(aspect_ratio), the width is min_size*sqrt(aspect_ratio). Defaul *@par Restrictions: *Warning: THIS FUNCTION IS DEPRECATED. Please use PriorBox instead. */ - REG_OP(PriorBoxD) - .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT})) - .INPUT(img, TensorType({DT_FLOAT16, DT_FLOAT})) - .INPUT(data_h, TensorType({DT_FLOAT16, DT_FLOAT})) - .INPUT(data_w, TensorType({DT_FLOAT16, DT_FLOAT})) - .INPUT(box_height, TensorType({DT_FLOAT16, DT_FLOAT})) - .INPUT(box_width, TensorType({DT_FLOAT16, DT_FLOAT})) - .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT})) - .REQUIRED_ATTR(min_size, ListFloat) - .REQUIRED_ATTR(max_size, ListFloat) - .ATTR(img_h, Int, 0) - .ATTR(img_w, Int, 0) - .ATTR(step_h, Float, 0.0) - .ATTR(step_w, Float, 0.0) - .ATTR(flip, Bool, true) - .ATTR(clip, Bool, false) - .ATTR(offset, Float, 0.5) - .ATTR(variance, ListFloat, {0.1}) - .OP_END_FACTORY_REG(PriorBoxD); +REG_OP(PriorBoxD) + .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(img, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(data_h, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(data_w, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(box_height, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(box_width, TensorType({DT_FLOAT16, DT_FLOAT})) + .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT})) + .REQUIRED_ATTR(min_size, ListFloat) + .REQUIRED_ATTR(max_size, ListFloat) + .ATTR(img_h, Int, 0) + .ATTR(img_w, Int, 0) + .ATTR(step_h, Float, 0.0) + .ATTR(step_w, Float, 0.0) + .ATTR(flip, Bool, true) + .ATTR(clip, Bool, false) + .ATTR(offset, Float, 0.5) + .ATTR(variance, ListFloat, {0.1}) + .OP_END_FACTORY_REG(PriorBoxD); /** *@brief Performs SSD prior box detection, with four additional matrices and the "aspect_ratio" attribute deleted compared to PriorBox . \n @@ -358,22 +358,22 @@ is min_size/sqrt(aspect_ratio), the width is min_size*sqrt(aspect_ratio). Defaul *@par Restrictions: *Warning: THIS FUNCTION IS DEPRECATED. Please use PriorBox instead. */ - REG_OP(PriorBoxDV2) - .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT})) - .INPUT(img, TensorType({DT_FLOAT16, DT_FLOAT})) - .INPUT(boxes, TensorType({DT_FLOAT16, DT_FLOAT})) - .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT})) - .REQUIRED_ATTR(min_size, ListFloat) - .REQUIRED_ATTR(max_size, ListFloat) - .ATTR(img_h, Int, 0) - .ATTR(img_w, Int, 0) - .ATTR(step_h, Float, 0.0) - .ATTR(step_w, Float, 0.0) - .ATTR(flip, Bool, true) - .ATTR(clip, Bool, false) - .ATTR(offset, Float, 0.5) - .ATTR(variance, ListFloat, {0.1}) - .OP_END_FACTORY_REG(PriorBoxDV2); +REG_OP(PriorBoxDV2) + .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(img, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(boxes, TensorType({DT_FLOAT16, DT_FLOAT})) + .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT})) + .REQUIRED_ATTR(min_size, ListFloat) + .REQUIRED_ATTR(max_size, ListFloat) + .ATTR(img_h, Int, 0) + .ATTR(img_w, Int, 0) + .ATTR(step_h, Float, 0.0) + .ATTR(step_w, Float, 0.0) + .ATTR(flip, Bool, true) + .ATTR(clip, Bool, false) + .ATTR(offset, Float, 0.5) + .ATTR(variance, ListFloat, {0.1}) + .OP_END_FACTORY_REG(PriorBoxDV2); /** *@brief Performs Position Sensitive ROI Pooling . \n @@ -531,10 +531,10 @@ as xx...xyy...yww...whh...hbb...bc0c0..c0c1c1...c1......cncn...cn . \n * It is a custom operator. It has no corresponding operator in Caffe. */ REG_OP(Yolo) - .INPUT(x, TensorType({DT_FLOAT16,DT_FLOAT})) - .OUTPUT(coord_data, TensorType({DT_FLOAT16,DT_FLOAT})) - .OUTPUT(obj_prob, TensorType({DT_FLOAT16,DT_FLOAT})) - .OUTPUT(classes_prob, TensorType({DT_FLOAT16,DT_FLOAT})) + .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT})) + .OUTPUT(coord_data, TensorType({DT_FLOAT16, DT_FLOAT})) + .OUTPUT(obj_prob, TensorType({DT_FLOAT16, DT_FLOAT})) + .OUTPUT(classes_prob, TensorType({DT_FLOAT16, DT_FLOAT})) .ATTR(boxes, Int, 3) .ATTR(coords, Int, 4) .ATTR(classes, Int, 80) @@ -584,10 +584,10 @@ REG_OP(Yolo) * It is a custom operator. It has no corresponding operator in Caffe. */ REG_OP(YoloV2DetectionOutput) - .INPUT(coord_data, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(obj_prob, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(classes_prob, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(img_info, TensorType({DT_FLOAT16,DT_FLOAT})) + .INPUT(coord_data, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(obj_prob, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(classes_prob, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(img_info, TensorType({DT_FLOAT16, DT_FLOAT})) .REQUIRED_ATTR(biases, ListFloat) .ATTR(boxes, Int, 5) .ATTR(coords, Int, 4) @@ -598,7 +598,7 @@ REG_OP(YoloV2DetectionOutput) .ATTR(score_threshold, Float, 0.5) .ATTR(iou_threshold, Float, 0.45) .ATTR(pre_nms_topn, Int, 512) - .OUTPUT(box_out, TensorType({DT_FLOAT16,DT_FLOAT})) + .OUTPUT(box_out, TensorType({DT_FLOAT16, DT_FLOAT})) .OUTPUT(box_out_num, TensorType({DT_INT32})) .OP_END_FACTORY_REG(YoloV2DetectionOutput) @@ -647,12 +647,12 @@ REG_OP(YoloV2DetectionOutput) *Warning: THIS FUNCTION IS DEPRECATED. Please use YoloV2DetectionOutput instead. */ REG_OP(YoloV2DetectionOutputD) - .INPUT(coord_data, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(obj_prob, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(classes_prob, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(img_info, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(windex, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(hindex, TensorType({DT_FLOAT16,DT_FLOAT})) + .INPUT(coord_data, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(obj_prob, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(classes_prob, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(img_info, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(windex, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(hindex, TensorType({DT_FLOAT16, DT_FLOAT})) .REQUIRED_ATTR(biases, ListFloat) .ATTR(boxes, Int, 5) .ATTR(coords, Int, 4) @@ -663,7 +663,7 @@ REG_OP(YoloV2DetectionOutputD) .ATTR(score_threshold, Float, 0.5) .ATTR(iou_threshold, Float, 0.45) .ATTR(pre_nms_topn, Int, 512) - .OUTPUT(box_out, TensorType({DT_FLOAT16,DT_FLOAT})) + .OUTPUT(box_out, TensorType({DT_FLOAT16, DT_FLOAT})) .OUTPUT(box_out_num, TensorType({DT_INT32})) .OP_END_FACTORY_REG(YoloV2DetectionOutputD) @@ -707,16 +707,16 @@ REG_OP(YoloV2DetectionOutputD) * It is a custom operator. It has no corresponding operator in Caffe. */ REG_OP(YoloV3DetectionOutput) - .INPUT(coord_data_low, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(coord_data_mid, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(coord_data_high, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(obj_prob_low, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(obj_prob_mid, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(obj_prob_high, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(classes_prob_low, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(classes_prob_mid, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(classes_prob_high, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(img_info, TensorType({DT_FLOAT16,DT_FLOAT})) + .INPUT(coord_data_low, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(coord_data_mid, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(coord_data_high, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(obj_prob_low, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(obj_prob_mid, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(obj_prob_high, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(classes_prob_low, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(classes_prob_mid, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(classes_prob_high, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(img_info, TensorType({DT_FLOAT16, DT_FLOAT})) .REQUIRED_ATTR(biases_low, ListFloat) .REQUIRED_ATTR(biases_mid, ListFloat) .REQUIRED_ATTR(biases_high, ListFloat) @@ -729,7 +729,7 @@ REG_OP(YoloV3DetectionOutput) .ATTR(score_threshold, Float, 0.5) .ATTR(iou_threshold, Float, 0.45) .ATTR(pre_nms_topn, Int, 512) - .OUTPUT(box_out, TensorType({DT_FLOAT16,DT_FLOAT})) + .OUTPUT(box_out, TensorType({DT_FLOAT16, DT_FLOAT})) .OUTPUT(box_out_num, TensorType({DT_INT32})) .OP_END_FACTORY_REG(YoloV3DetectionOutput) @@ -776,22 +776,22 @@ s *Warning: THIS FUNCTION IS DEPRECATED. Please use YoloV3DetectionOutput instead. */ REG_OP(YoloV3DetectionOutputD) - .INPUT(coord_data_low, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(coord_data_mid, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(coord_data_high, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(obj_prob_low, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(obj_prob_mid, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(obj_prob_high, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(classes_prob_low, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(classes_prob_mid, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(classes_prob_high, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(img_info, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(windex1, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(windex2, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(windex3, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(hindex1, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(hindex2, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(hindex3, TensorType({DT_FLOAT16,DT_FLOAT})) + .INPUT(coord_data_low, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(coord_data_mid, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(coord_data_high, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(obj_prob_low, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(obj_prob_mid, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(obj_prob_high, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(classes_prob_low, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(classes_prob_mid, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(classes_prob_high, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(img_info, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(windex1, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(windex2, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(windex3, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(hindex1, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(hindex2, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(hindex3, TensorType({DT_FLOAT16, DT_FLOAT})) .REQUIRED_ATTR(biases_low, ListFloat) .REQUIRED_ATTR(biases_mid, ListFloat) .REQUIRED_ATTR(biases_high, ListFloat) @@ -804,7 +804,7 @@ REG_OP(YoloV3DetectionOutputD) .ATTR(score_threshold, Float, 0.5) .ATTR(iou_threshold, Float, 0.45) .ATTR(pre_nms_topn, Int, 512) - .OUTPUT(box_out, TensorType({DT_FLOAT16,DT_FLOAT})) + .OUTPUT(box_out, TensorType({DT_FLOAT16, DT_FLOAT})) .OUTPUT(box_out_num, TensorType({DT_INT32})) .OP_END_FACTORY_REG(YoloV3DetectionOutputD) @@ -848,7 +848,7 @@ There are three Yolo operators at Yolov3DetectionOutput's preceding layer on Yol * It is a custom operator. It has no corresponding operator in Caffe. */ REG_OP(YoloV3DetectionOutputV2) - .DYNAMIC_INPUT(x, TensorType({DT_FLOAT16,DT_FLOAT})) + .DYNAMIC_INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT})) .REQUIRED_ATTR(biases, ListFloat) .ATTR(boxes, Int, 3) .ATTR(coords, Int, 4) @@ -862,7 +862,7 @@ REG_OP(YoloV3DetectionOutputV2) .ATTR(N, Int, 10) .ATTR(resize_origin_img_to_net, Bool, false) .ATTR(out_box_dim, Int, 3) - .OUTPUT(box_out, TensorType({DT_FLOAT16,DT_FLOAT})) + .OUTPUT(box_out, TensorType({DT_FLOAT16, DT_FLOAT})) .OUTPUT(box_out_num, TensorType({DT_INT32})) .OP_END_FACTORY_REG(YoloV3DetectionOutputV2) @@ -910,9 +910,9 @@ REG_OP(YoloV3DetectionOutputV2) * Warning: THIS FUNCTION IS DEPRECATED. Please use YoloV3DetectionOutputV2 instead. */ REG_OP(YoloV3DetectionOutputV2D) - .DYNAMIC_INPUT(x, TensorType({DT_FLOAT16,DT_FLOAT})) - .DYNAMIC_INPUT(windex, TensorType({DT_FLOAT16,DT_FLOAT})) - .DYNAMIC_INPUT(hindex, TensorType({DT_FLOAT16,DT_FLOAT})) + .DYNAMIC_INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT})) + .DYNAMIC_INPUT(windex, TensorType({DT_FLOAT16, DT_FLOAT})) + .DYNAMIC_INPUT(hindex, TensorType({DT_FLOAT16, DT_FLOAT})) .REQUIRED_ATTR(biases, ListFloat) .ATTR(boxes, Int, 3) .ATTR(coords, Int, 4) @@ -926,7 +926,7 @@ REG_OP(YoloV3DetectionOutputV2D) .ATTR(N, Int, 10) .ATTR(resize_origin_img_to_net, Bool, false) .ATTR(out_box_dim, Int, 3) - .OUTPUT(box_out, TensorType({DT_FLOAT16,DT_FLOAT})) + .OUTPUT(box_out, TensorType({DT_FLOAT16, DT_FLOAT})) .OUTPUT(box_out_num, TensorType({DT_INT32})) .OP_END_FACTORY_REG(YoloV3DetectionOutputV2D) @@ -1466,9 +1466,9 @@ REG_OP(NormalizeBBox) * y: A Tensor. Must have the same type as box_predictions. */ REG_OP(DecodeBboxV2) - .INPUT(boxes, TensorType({DT_FLOAT16,DT_FLOAT})) - .INPUT(anchors, TensorType({DT_FLOAT16,DT_FLOAT})) - .OUTPUT(y, TensorType({DT_FLOAT16,DT_FLOAT})) + .INPUT(boxes, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(anchors, TensorType({DT_FLOAT16, DT_FLOAT})) + .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT})) .ATTR(scales, ListFloat, {1.0, 1.0, 1.0, 1.0}) .ATTR(decode_clip, Float, 0.0) .ATTR(reversed_box, Bool, false) @@ -1592,7 +1592,6 @@ selected indices from the boxes tensor, where M <= max_output_size. \n *Compatible with onnx NonMaxSuppression operator. */ - REG_OP(NonMaxSuppressionV7) .INPUT(boxes, TensorType({DT_FLOAT16, DT_FLOAT})) .INPUT(scores, TensorType({DT_FLOAT16, DT_FLOAT})) @@ -1641,7 +1640,7 @@ REG_OP(RoiExtractor) .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT})) .ATTR(finest_scale, Int, 56) .ATTR(roi_scale_factor, Float, 0) - .ATTR(spatial_scale, ListFloat, { 1.f/4, 1.f/8, 1.f/16, 1.f/32 }) + .ATTR(spatial_scale, ListFloat, {1.f / 4, 1.f / 8, 1.f / 16, 1.f / 32}) .ATTR(pooled_height, Int, 7) .ATTR(pooled_width, Int, 7) .ATTR(sample_num, Int, 0) @@ -1649,6 +1648,84 @@ REG_OP(RoiExtractor) .ATTR(aligned, Bool, true) .OP_END_FACTORY_REG(RoiExtractor) +/** +*@brief Performs Position Sensitive PS ROI Pooling . \n + +*@par Inputs: +* Two inputs, including: +*@li x: An NC1HWC0 tensor of type float16 or float32, describing the feature +* map, dimension C1 must be equal to +* (int(output_dim+15)/C0))*group_size*group_size. +*@li rois: A tensor of type float16 or float32, with shape +* [batch, 5, rois_num], describing the ROIs, each ROI consists of five +* elements: "batch_id", "x1", "y1", "x2", and "y2", which "batch_id" indicates +* the index of the input feature map, "x1", "y1", "x2", or "y2" must be +* greater than or equal to "0.0" . \n + +*@par Attributes: +*@li output_dim: A required int32, specifying the number of output channels, +* must be greater than 0. +*@li group_size: A required int32, specifying the number of groups to encode +* position-sensitive score maps, must be within the range (0, 128). +*@li spatial_scale: A required float32, scaling factor for mapping the input +* coordinates to the ROI coordinates . \n + +*@par Outputs: +*y: An NC1HWC0 tensor of type float16 or float32, describing the result +* feature map . \n + +*@attention Constraints: +* HC1HWC0: channel must be Group_size squared, rois_num is a multiple of 16 +*/ +REG_OP(PSROIPoolingV2) + .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(rois, TensorType({DT_FLOAT16, DT_FLOAT})) + .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT})) + .REQUIRED_ATTR(spatial_scale, Float) + .REQUIRED_ATTR(output_dim, Int) + .REQUIRED_ATTR(group_size, Int) + .OP_END_FACTORY_REG(PSROIPoolingV2) + +/** +*@brief Performs Position Sensitive PS ROI Pooling Grad . \n + +*@par Inputs: +* Two inputs, including: +*@li x: An NC1HWC0 tensor of type float16 or float32, describing the result +* feature map . \n +*@li rois: A tensor of type float16 or float32, with shape +* [batch, 5, rois_num], describing the ROIs, each ROI consists of five +* elements: "batch_id", "x1", "y1", "x2", and "y2", which "batch_id" indicates +* the index of the input feature map, "x1", "y1", "x2", or "y2" must be +* greater than or equal to "0.0" . \n + +*@par Attributes: +*@li output_dim: A required int32, specifying the number of output channels, +* must be greater than 0. +*@li group_size: A required int32, specifying the number of groups to encode +* position-sensitive score maps, must be within the range (0, 128). +*@li spatial_scale: A required float32, scaling factor for mapping the input +* coordinates to the ROI coordinates . \n +*@li input_size: A required listInt, mapping the gradinput size: (H, W) + +*@par Outputs: +*y: An NC1HWC0 tensor of type float16 or float32, describing the feature +* map, dimension C1 must be equal to +* (int(output_dim+15)/C0))*group_size*group_size. + +*@attention Constraints: +* HC1HWC0: channel must be Group_size squared, rois_num is a multiple of 16 +*/ +REG_OP(PSROIPoolingGradV2D) + .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT})) + .INPUT(rois, TensorType({DT_FLOAT16, DT_FLOAT})) + .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT})) + .REQUIRED_ATTR(spatial_scale, Float) + .REQUIRED_ATTR(output_dim, Int) + .REQUIRED_ATTR(group_size, Int) + .REQUIRED_ATTR(input_size, ListInt) + .OP_END_FACTORY_REG(PSROIPoolingGradV2D) + } // namespace ge #endif // OPS_BUILT_IN_OP_PROTO_INC_NN_DETECT_OPS_H_ diff --git a/third_party/fwkacllib/inc/ops/nn_norm_ops.h b/third_party/fwkacllib/inc/ops/nn_norm_ops.h index 7d38beb5..2bc87ec1 100644 --- a/third_party/fwkacllib/inc/ops/nn_norm_ops.h +++ b/third_party/fwkacllib/inc/ops/nn_norm_ops.h @@ -525,6 +525,31 @@ REG_OP(LayerNorm) .ATTR(epsilon, Float, 0.0000001) .OP_END_FACTORY_REG(LayerNorm) +/** +*@brief Returns a tensor where each sub-tensor of input along dimension +* dim is normalized such that the p-norm of the sub-tensor is lower than the value maxnorm. \n + +*@par Inputs: +*One input, including: +* @li x: A Tensor. Must be one of the following types: float16, float32 . \n + +*@par Attributes: +* @li p: Specify L_p norm, the type is float. +* @li dim: The processed dim, the type is int. +* @li maxnorm: Threshold for comparison, the type is float. \n + +*@par Outputs: +*One outputs, including: +* @li y: shape and dtype of output, should be same shape and type as input. +*/ +REG_OP(Renorm) + .INPUT(x, TensorType::BasicType()) + .OUTPUT(y, TensorType::BasicType()) + .REQUIRED_ATTR(p, Float) + .REQUIRED_ATTR(dim, Int) + .REQUIRED_ATTR(maxnorm, Float) + .OP_END_FACTORY_REG(Renorm) + /** *@brief LayerNormGrad operator interface implementation * calculating: dy, x, variance, mean, gamma diff --git a/third_party/fwkacllib/inc/ops/nn_pooling_ops.h b/third_party/fwkacllib/inc/ops/nn_pooling_ops.h index 32eb148b..8251fac3 100644 --- a/third_party/fwkacllib/inc/ops/nn_pooling_ops.h +++ b/third_party/fwkacllib/inc/ops/nn_pooling_ops.h @@ -397,8 +397,8 @@ No default value. specifying the stride of the sliding window for each dimension of the input tensor. No default value. *@li padding: A required string type of float16. -*@li pads: A list type of int32. Default value {0, 0, 0}. -*@li dilation: A list type of int32. Default value {1, 1, 1}. +*@li pads: A list type of int32. Default value {0,0,0,0,0,0}. +*@li dilation: A list type of int32. Default value {1,1,1,1,1,1}. *@li ceil_mode: A ceil mode number of int32 . Default value 0. *@li data_format: An optional string. Defaults to "NDHWC" . \n @@ -421,8 +421,8 @@ REG_OP(MaxPool3D) .REQUIRED_ATTR(ksize, ListInt) .REQUIRED_ATTR(strides, ListInt) .REQUIRED_ATTR(padding, String) - .ATTR(pads, ListInt, {0,0,0}) - .ATTR(dilation, ListInt, {1,1,1}) + .ATTR(pads, ListInt, {0,0,0,0,0,0}) + .ATTR(dilation, ListInt, {1,1,1,1,1,1}) .ATTR(ceil_mode, Int, 0) .ATTR(data_format, String, "NDHWC") .OP_END_FACTORY_REG(MaxPool3D) diff --git a/third_party/fwkacllib/inc/ops/pad_ops.h b/third_party/fwkacllib/inc/ops/pad_ops.h index 50eb98c8..42da3828 100644 --- a/third_party/fwkacllib/inc/ops/pad_ops.h +++ b/third_party/fwkacllib/inc/ops/pad_ops.h @@ -418,7 +418,7 @@ REG_OP(EmbeddingRankId) */ REG_OP(FillV2) .INPUT(dims, TensorType({DT_INT16, DT_INT32, DT_INT64})) - .OUTPUT(y, TensorType({DT_FLOAT, DT_FLOAT, DT_DOUBLE, DT_INT8, DT_INT16, DT_INT32, DT_INT64})) + .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE, DT_INT8, DT_INT16, DT_INT32, DT_INT64})) .ATTR(value, Float, 0) .OP_END_FACTORY_REG(FillV2) @@ -437,7 +437,7 @@ REG_OP(FillV2) * Compatible with the ONNX operator ConstantOfShape. */ REG_OP(FillV2D) - .OUTPUT(y, TensorType({DT_FLOAT, DT_FLOAT, DT_DOUBLE, DT_INT8, DT_UINT8, DT_INT16, DT_INT32, DT_INT64})) + .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE, DT_INT8, DT_UINT8, DT_INT16, DT_INT32, DT_INT64})) .ATTR(value, Float, 0) .REQUIRED_ATTR(dims, ListInt) .OP_END_FACTORY_REG(FillV2D)