Hi,
I have added a new layer and successfully passed the model import phase.
But it seems to have error when doing quantization.
I have re-built the quantools and test tools by instruction "make RUN_REF_FOR_STATS=1 TARGET_PLATFORM=PC" and "make TARGET_PLATFORM=PC" respectively.
It seems to miss the layer and message shows as below:
Processing config file #0 : /home/tda4dev/psdk_rtos_auto_j7_06_01_00_15/tidl_j7_01_00_00_00/ti_dl/utils/tidlModelImport/tempDir/qunat_stats_config.txt
Error at line: 208 : in file src/tidl_tb.c, of function : tidl_tb_algCreate
Error Type: TIDL_E_UNSUPPORTED_LAYER
Error at line: 479 : in file src/tidl_tb.c, of function : tidlMultiInstanceTest
Error Type: TIDL_E_UNSUPPORTED_LAYER
Main iteration numer: 0....
Preparing for memory allocation : internal iteration number: 0
successful Memory allocation
-------------------- Network Compiler : Analysis Results are available --------------------
SUGGESTION: [TIDL_Deconv2DLayer] deconv3_up Please change to Upsample/Resize if possible. Upsample/Resize will be more efficient.
SUGGESTION: [TIDL_Deconv2DLayer] deconv2 Please change to Upsample/Resize if possible. Upsample/Resize will be more efficient.
SUGGESTION: [TIDL_Deconv2DLayer] deconv1 Please change to Upsample/Resize if possible. Upsample/Resize will be more efficient.
****************************************************
** ALL MODEL CHECK PASSED **
****************************************************
Here I have a question about custom layer, if it is necessary that new layer should be customlayer?
For example , I want to create a new layer called newlayer.
Then I added #define TIDL_newLayer ((int32_t) 25) in the itidl_ti.h file , changing #define TIDL_UnsupportedLayer ((int32_t) from 25 to 26.
Thank you,
Kevin.
