Linux (AARCH64) Deployment

Question/Issue:
There are some warning when deploy to Linux (AARCH64)

Project ID:
510570

here the logs
Scheduling job in cluster…
Container image pulled!
Job started
Writing templates…
Scheduling job in cluster…
Container image pulled!
Job started
Exporting TensorFlow Lite model…
Exporting TensorFlow Lite model OK

Removing clutter…
Removing clutter OK

Copying output…
Copying output OK

Scheduling job in cluster…
Container image pulled!
Job started
Building binary…
aarch64-linux-gnu-g++ -Wall -g -Wno-strict-aliasing -I. -Isource -Imodel-parameters -Itflite-model -Ithird_party/ -Iutils/ -Os -DNDEBUG -DEI_CLASSIFIER_ENABLE_DETECTION_POSTPROCESS_OP=1 -g -DEI_CLASSIFIER_USE_FULL_TFLITE=1 -Iedge-impulse-sdk/tensorflow-lite -DDISABLEFLOAT16 -std=c++17 -c source/main.cpp -o source/main.o
In file included from ./edge-impulse-sdk/classifier/ei_classifier_types.h:23,
from ./edge-impulse-sdk/classifier/ei_model_types.h:23,
from ./edge-impulse-sdk/classifier/ei_run_classifier.h:21,
from source/main.cpp:9:
./model-parameters/model_metadata.h:104:2: warning: #warning ‘EI_CLASSFIER_OBJECT_DETECTION_COUNT’ is used for the guaranteed minimum number of objects detected. To get all objects during inference use ‘bounding_boxes_count’ from the ‘ei_impulse_result_t’ struct instead. [-Wcpp]
#warning ‘EI_CLASSFIER_OBJECT_DETECTION_COUNT’ is used for the guaranteed minimum number of objects detected. To get all objects during inference use ‘bounding_boxes_count’ from the ‘ei_impulse_result_t’ struct instead.
^~~~~~~
In file included from ./tensorflow-lite/tensorflow/lite/core/subgraph.h:39,
from ./tensorflow-lite/tensorflow/lite/core/async/async_subgraph.h:27,
from ./tensorflow-lite/tensorflow/lite/core/async/async_signature_runner.h:24,
from ./tensorflow-lite/tensorflow/lite/core/interpreter.h:45,
from ./tensorflow-lite/tensorflow/lite/interpreter.h:21,
from ./edge-impulse-sdk/classifier/inferencing_engines/tflite_full.h:28,
from ./edge-impulse-sdk/classifier/ei_run_classifier.h:46,
from source/main.cpp:9:
./tensorflow-lite/tensorflow/lite/graph_info.h:125:1: warning: multi-line comment [-Wcomment]
// /------------
^
./tensorflow-lite/tensorflow/lite/graph_info.h:137:1: warning: multi-line comment [-Wcomment]
// /------------
^
In file included from ./edge-impulse-sdk/classifier/inferencing_engines/tflite_full.h:33,
from ./edge-impulse-sdk/classifier/ei_run_classifier.h:46,
from source/main.cpp:9:
./edge-impulse-sdk/classifier/ei_fill_result_struct.h: In function ‘bool ei_cube_check_overlap(ei_classifier_cube_t*, int, int, int, int, float)’:
./edge-impulse-sdk/classifier/ei_fill_result_struct.h:84:45: warning: comparison of integer expressions of different signedness: ‘size_t’ {aka ‘long unsigned int’} and ‘int’ [-Wsign-compare]
bool is_overlapping = !(c->x + c->width < x || c->y + c->height < y || c->x > x + width || c->y > y + height);

./edge-impulse-sdk/classifier/ei_fill_result_struct.h:84:69: warning: comparison of integer expressions of different signedness: 'size_t' {aka 'long unsigned int'} and 'int' [-Wsign-compare]
bool is_overlapping = !(c->x + c->width < x || c->y + c->height < y || c->x > x + width || c->y > y + height);
~~~~~~~~~~~~~~~~~^~~
./edge-impulse-sdk/classifier/ei_fill_result_struct.h:84:81: warning: comparison of integer expressions of different signedness: 'size_t' {aka 'long unsigned int'} and 'int' [-Wsign-compare]
bool is_overlapping = !(c->x + c->width < x || c->y + c->height < y || c->x > x + width || c->y > y + height);
~~~~~^~~~~~~~~~~
./edge-impulse-sdk/classifier/ei_fill_result_struct.h:84:101: warning: comparison of integer expressions of different signedness: 'size_t' {aka 'long unsigned int'} and 'int' [-Wsign-compare]
bool is_overlapping = !(c->x + c->width < x || c->y + c->height < y || c->x > x + width || c->y > y + height);
~~~~~^~~~~~~~~~~~
./edge-impulse-sdk/classifier/ei_fill_result_struct.h:88:11: warning: comparison of integer expressions of different signedness: 'int' and 'size_t' {aka 'long unsigned int'} [-Wsign-compare]
if (x < c->x) {
~~^~~~~~
./edge-impulse-sdk/classifier/ei_fill_result_struct.h:94:11: warning: comparison of integer expressions of different signedness: 'int' and 'size_t' {aka 'long unsigned int'} [-Wsign-compare]
if (y < c->y) {
~~^~~~~~
./edge-impulse-sdk/classifier/ei_fill_result_struct.h:100:19: warning: comparison of integer expressions of different signedness: 'int' and 'size_t' {aka 'long unsigned int'} [-Wsign-compare]
if (x + width > c->x + c->width) {
~~~~~~~~~~^~~~~~~~~~~~~~~~~
./edge-impulse-sdk/classifier/ei_fill_result_struct.h:105:20: warning: comparison of integer expressions of different signedness: 'int' and 'size_t' {aka 'long unsigned int'} [-Wsign-compare]
if (y + height > c->y + c->height) {
~~~~~~~~~~~^~~~~~~~~~~~~~~~~~
./edge-impulse-sdk/classifier/ei_fill_result_struct.h: In function 'void fill_result_struct_from_cubes(ei_impulse_result_t*, std::vector<cube*>*, int, uint32_t)':
./edge-impulse-sdk/classifier/ei_fill_result_struct.h:190:27: warning: comparison of integer expressions of different signedness: 'int' and 'uint32_t' {aka 'unsigned int'} [-Wsign-compare]
if (added_boxes_count < object_detection_count) {
~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~
./edge-impulse-sdk/classifier/ei_fill_result_struct.h: In function 'EI_IMPULSE_ERROR fill_result_struct_f32_fomo(const ei_impulse_t*, const ei_learning_block_config_tflite_graph_t*, ei_impulse_result_t*, float*, int, int)':
./edge-impulse-sdk/classifier/ei_fill_result_struct.h:217:26: warning: comparison of integer expressions of different signedness: 'size_t' {aka 'long unsigned int'} and 'int' [-Wsign-compare]
for (size_t y = 0; y < out_width; y++) {
~~^~~~~~~~~~~
./edge-impulse-sdk/classifier/ei_fill_result_struct.h:219:30: warning: comparison of integer expressions of different signedness: 'size_t' {aka 'long unsigned int'} and 'int' [-Wsign-compare]
for (size_t x = 0; x < out_height; x++) {
~~^~~~~~~~~~~~
./edge-impulse-sdk/classifier/ei_fill_result_struct.h:222:36: warning: comparison of integer expressions of different signedness: 'size_t' {aka 'long unsigned int'} and 'int' [-Wsign-compare]
for (size_t ix = 1; ix < impulse->label_count + 1; ix++) {
~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
./edge-impulse-sdk/classifier/ei_fill_result_struct.h: In function 'EI_IMPULSE_ERROR fill_result_struct_i8_fomo(const ei_impulse_t*, const ei_learning_block_config_tflite_graph_t*, ei_impulse_result_t*, int8_t*, float, float, int, int)':
./edge-impulse-sdk/classifier/ei_fill_result_struct.h:251:26: warning: comparison of integer expressions of different signedness: 'size_t' {aka 'long unsigned int'} and 'int' [-Wsign-compare]
for (size_t y = 0; y < out_width; y++) {
~~^~~~~~~~~~~
./edge-impulse-sdk/classifier/ei_fill_result_struct.h:253:30: warning: comparison of integer expressions of different signedness: 'size_t' {aka 'long unsigned int'} and 'int' [-Wsign-compare]
for (size_t x = 0; x < out_height; x++) {
~~^~~~~~~~~~~~
./edge-impulse-sdk/classifier/ei_fill_result_struct.h:256:36: warning: comparison of integer expressions of different signedness: 'size_t' {aka 'long unsigned int'} and 'int' [-Wsign-compare]
for (size_t ix = 1; ix < impulse->label_count + 1; ix++) {
~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
aarch64-linux-gnu-g++ -Wall -g -Wno-strict-aliasing -I. -Isource -Imodel-parameters -Itflite-model -Ithird_party/ -Iutils/ -Os -DNDEBUG -DEI_CLASSIFIER_ENABLE_DETECTION_POSTPROCESS_OP=1 -g -DEI_CLASSIFIER_USE_FULL_TFLITE=1 -Iedge-impulse-sdk/tensorflow-lite -DDISABLEFLOAT16 -std=c++17 -c tflite-model/tflite_learn_69.cpp -o tflite-model/tflite_learn_69.o
mkdir -p build

Hello @nugro,

These are warnings only, I see them too when I choose the Linux AARCH64 deployment methods but I can build and run my models properly on the devices.

Best,

Louis