Add support for full tflite deployments

[faradayberry]

Added support for full tflite deployments as tested with object detection and image classification models, as well as checking for YOLOV5 to add appropriate suffix in ei_fill_result_struct.h and fix issue #11167. This includes updates to:

EIDownload.py

• Added print of error response for easier troubleshooting

generate.py

• Added --full-tflite argument to use tflite instead of default EON
• Updated edit_file function to handle includes
• Added a function check_for_yolov5 to return True if any model data indicates YOLOV5 and if so an additional modification is made in ei_fill_result_struct.h to append the project suffix to pattern _ei_classifier_inferencingcategories
• Added a function insert_define_statement to insert a new #define after the #includes and before the rest of any #defines
• Added functions insert_after_line, replace_line, and remove_line to perform these operations in some files as required by the full tflite changes
• Added a function merge_tflite_full to merge the projects' tflite_full.h #includes for pattern _trained_model_opsdefine
• Added an else to if "compiled" in f: to cover case when built files don't have "compiled" in the name

In main loop added check for tflite and made additional updates:

• Insert #define EI_CLASSIFIER_USE_FULL_TFLITE 1 in model_metadata.h
• Remove deprecated API reference in tflite_full.h
• Edit Zephyr cmake to use full tflite

At the end added use of merge_tflite_full to merge all the #includes for _trained_model_opsdefine

[luisomoreau]

I saw plenty of issues, including the object detection support when it is not the first impulse to be downloaded and merged. I created this other PR from this one that uses a custom_display function to avoid the #if statement that are not available from the merged model_metadata.h. e.g #define EI_CLASSIFIER_OBJECT_DETECTION 0

https://github.com/edgeimpulse/multi-impulse-deployment-block/pull/5

[AlessandroEdge]

Is this ready to be merged and will it address https://github.com/edgeimpulse/edgeimpulse/issues/11167?

[faradayberry]

Is this ready to be merged and will it address edgeimpulse/edgeimpulse#11167?

I haven't made any changes to address @luisomoreau concerns from above, I can only confirm it works for the combination I needed it for, an object detector as the main project (with sometimes deploying YOLOV5, other times TAO) and an image classifier as the other project.

[AlessandroEdge]

Ok let's wait for Louis to be back

[AIWintermuteAI]

Okay, should have pushed my changes earlier... I started working on multi-impulse block fixes last week, as per internal repo issue #11564. Few comments:

Added --full-tflite argument to use tflite instead of default EON

Should just be --tflite or --non-eon.

Added a function check_for_yolov5 to return True if any model data indicates YOLOV5 and if so an additional modification is made in ei_fill_result_struct.h to append the project suffix to pattern ei_classifier_inferencing_categories

This needs to be fixed in SDK. When it is fixed we can remove YOLOv5 check.

I'll take a look at other changes.