# Machine learning APIs

The ML APIs allow configurations for the tensor-specific requirements and machine
        learning properties.

- **[GstMLType](https://docs.qualcomm.com/doc/80-70014-50/topic/ml-api-gstmltype.html)**  

GstMLType enables you to get information on the GStreamer ML data types.
- **[GstMLInfo](https://docs.qualcomm.com/doc/80-70014-50/topic/ml-api-gstmlinfo.html)**  

GstMLInfo represents the information structure describing the machine learning         properties. This information can be filled in from GstCaps with             gst\_ml\_info\_from\_caps().
- **[GstMLTensorMeta](https://docs.qualcomm.com/doc/80-70014-50/topic/ml-api-gstmltensormeta.html)**  

GstMLTensorMeta defines the metadata API for different tensor types.
- **[GstMLFrame](https://docs.qualcomm.com/doc/80-70014-50/topic/ml-api-gstmlframe.html)**  

GstMLFrame is a convenient structure obtained from             gst\_ml\_frame\_map(), containing mapped pointers to the tensors and the         required information about them.
- **[GstMLBufferPool](https://docs.qualcomm.com/doc/80-70014-50/topic/ml-api-gstmlbufferpool.html)**  

GstMLBufferPool is a special GstBufferPool subclass for ML tensor buffers. It allows         you to configure the tensor-specific requirements such as multiple [GstMemory](https://gstreamer.freedesktop.org/documentation/gstreamer/gstmemory.html?gi-language=c) blocks in a single [GstBuffer](https://gstreamer.freedesktop.org/documentation/gstreamer/gstbuffer.html?gi-language=c).

**Parent Topic:** [Base utility APIs](https://docs.qualcomm.com/doc/80-70014-50/topic/im-sdk-base-uitilities.html)

Last Published: Oct 27, 2025

[Previous Topic
GstGlesVideoConverter APIs](https://docs.qualcomm.com/bundle/publicresource/80-70014-50/topics/gstglesvideoconverter-apis.md) [Next Topic
GstMLType](https://docs.qualcomm.com/bundle/publicresource/80-70014-50/topics/ml-api-gstmltype.md)