![]() Existing users can use CMSIS 5.9.0 release to continue using it.Īs a consequence of this, the data type aliases q7_t, q15_t, q31_t and q63_t are replaced by int8_t, int16_t, int32_t, int64_t respectively. Neural Network(NN) operators which do not follow the quantization specification of TensorFlow Lite for Microcontrollers is removed. It is reccomended that users change the return type in their applications. This is now replaced by enum 'arm_cmsis_nn_status'. CMSIS-NN used error codes from CMSIS-DSP in the form of enum 'arm_status'. ![]() The return type of all API's that returned a status is now changed. ![]() * Fix 'asm operand has impossible constraint' error for certain combination of GCC compiler related to MVE optimizations. * Fix error in buffer size calculation of DW Convolution wrapper for int8. * Workaround for a GCC 12.2 Internal Compiler Error affecting MVE. * Fix selection of correct int16 DW Convolution function. * Potential out of buffer write in SVDF state data. * A new DS_CNN_S model unit test is added that is used in End-to-End benchmark (). CMSIS-NN can be built without including any other CMSIS module. * Get size of buffers on host to support TVM use case. * Script to extract model hyperparameters. * Improvements in LSTM, generic convolution and int8/int16 elementwise mul for DSP extension. * Improvements in LSTM, generic convolution, 1xN convolution, DW convolution and FC for MVE extension. The following are the updates compared to previous release in ()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |