# Steps to create `srnet` module Source: [https://docs.qualcomm.com/doc/80-70015-15B/topic/steps-to-create-srnet-module.html](https://docs.qualcomm.com/doc/80-70015-15B/topic/steps-to-create-srnet-module.html) 1. Create module header “gst-plugins-qti-oss/gst-plugin-base/gst/ml/ml-module-video-super-resolution.h” - Reference from existing plugin: [gst-plugin-base/gst/ml/ml-module-video-super-resolution.h · imsdk.lnx.2.0.0.r2-rel · CodeLinaro / le / platform / vendor / qcom-opensource / gst-plugins-qti-oss · GitLab](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/blob/imsdk.lnx.2.0.0.r2-rel/gst-plugin-base/gst/ml/ml-module-video-super-resolution.h?ref_type=heads) - Import required gst headers - Create GST_API gboolean gst_ml_module_video_super_resolution_execute (GstMLModule * module, GstMLFrame * mlframe, GstVideoFrame * vframe);Copy to clipboard - This function is required to call post-processing function (gst\_ml\_module\_process) which will be defined in ml-vsuperresolution-<module-name>.c 2. Create module "gst-plugins-mlvsuperresolution/modules/ml-vsuperresolution-srnet.c" - Reference from existing plugin: [gst-plugin-mlvsegmentation/modules/ml-vsegmentation-deeplab-argmax.c · imsdk.lnx.2.0.0.r1-rel · CodeLinaro / le / platform / vendor / qcom-opensource / gst-plugins-qti-oss · GitLab](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/blob/imsdk.lnx.2.0.0.r1-rel/gst-plugin-mlvsegmentation/modules/ml-vsegmentation-deeplab-argmax.c?ref_type=heads) - Import "modules/ml-video-superresolution-module.h" header - Define model output caps #define GST_ML_MODULE_CAPS \ "neural-network/tensors, " \ "type = (string) { INT8, UINT8, INT32, FLOAT32 }, " \ "dimensions = (int) < <1, [32, 4096], [32, 4096]> >; " \ "neural-network/tensors, " \ "type = (string) { INT8, UINT8, INT32, FLOAT32 }, " \ "dimensions = (int) < <1, [32, 4096], [32, 4096], [1, 3]> >"Copy to clipboard **For Example** - Download [QuickSRNetLarge-Quantized- Qualcomm AI Hub](https://aihub.qualcomm.com/iot/models/quicksrnetlarge_quantized) model from AI Hub - Check output dimensions of the TFLite model (Refer to [Integrate AI Hub models in an application](https://docs.qualcomm.com/doc/80-70015-15B/topic/integrate-aihub-model.html)) - Format: dtype[N x H X W X C] - In the above module output caps <1, [32, 4096], [32, 4096], [1, 3]> - N = 1 -> Model Output Batch size - H = [32,4096] -> Model Output Height should be in this range - W= [32,4096] -> Model Output Width should be in this range - C = [1,3] -> Model Output Channels should be in this range - dtype = int8 for quantized models | float32 for non-quantized models - For Quantized models, Check output node for scale and offset - Format: scale\*(q-offset) - Implement following functions - Init - `gpointer gst_ml_module_open (void);` - De-init - `void gst_ml_module_close (gpointer instance);` - Caps - `GstCaps *gst_ml_module_caps (void);` - Configure - `gboolean gst_ml_module_configure (gpointer instance, GstStructure * settings);` - Check for module dtype, scale, and offset - De-quantize gdouble gst_ml_tensor_extract_value (GstMLType mltype, gpointer data, guint idx, gdouble offset, gdouble scale)Copy to clipboard - Scale and offset values need to passed for quantized models - Post-process - `gboolean gst_ml_module_process (gpointer instance, GstMLFrame*mlframe, gpointer output);` - Inferenced buffer - `indata = GST_ML_FRAME_BLOCK_DATA (mlframe, 0);` Output buffer to be filled with post-processed data - `outdata = GST_VIDEO_FRAME_PLANE_DATA (vframe, 0);` Data type of model - `mltype = GST_ML_FRAME_TYPE (mlframe);` Post-process (for super resolution) for (row = 0; row < GST_VIDEO_FRAME_HEIGHT (vframe); row++) { for (column = 0; column < GST_VIDEO_FRAME_WIDTH (vframe); column++) { // Calculate the destination index. idx = (((row * GST_VIDEO_FRAME_WIDTH (vframe)) + column) * bpp) + (row * padding); outdata[idx] = gst_ml_tensor_extract_value (mltype, indata, idx, submodule->qoffsets[0], submodule->qscales[0]); outdata[idx + 1] = gst_ml_tensor_extract_value (mltype, indata, (idx + 1), submodule->qoffsets[0], submodule->qscales[0]); outdata[idx + 2] = gst_ml_tensor_extract_value (mltype, indata, (idx + 2), submodule->qoffsets[0], submodule->qscales[0]); // If output has an alpha channel set it to opaque. if (bpp == 4) outdata[idx + 3] = 0xFF; } }Copy to clipboard - Update module name "gst-plugins-mlvsuperresolution/modules/CMakeLists.txt" - Reference from existing plugin: [gst-plugin-mlvsegmentation/modules/CMakeLists.txt · imsdk.lnx.2.0.0.r1-rel · CodeLinaro / le / platform / vendor / qcom-opensource / gst-plugins-qti-oss · GitLab](https://git.codelinaro.org/clo/le/platform/vendor/qcom-opensource/gst-plugins-qti-oss/-/blob/imsdk.lnx.2.0.0.r1-rel/gst-plugin-mlvsegmentation/modules/CMakeLists.txt?ref_type=heads) Last Published: Jan 21, 2026 [Previous Topic Overview of Module](https://docs.qualcomm.com/bundle/publicresource/80-70015-15B/topics/overview-of-module.md) [Next Topic Steps to update BitBake files for plugin compilation](https://docs.qualcomm.com/bundle/publicresource/80-70015-15B/topics/steps-to-update-bitbake-for-compilation.md)