arduino/arduinotensorflowlitetutorials

Machine Learning on Arduino

Arduino TensorFlow Lite Tutorials

This Github repo contains tutorials for using TensorFlow Lite on Arduino hardware.

• GestureToEmoji
  • Use the Arduino Nano 33 BLE Sense to convert motion gestures to emojis
• FruitToEmoji
  • Use the Arduino Nano 33 BLE Sense to classify fruit using the RGB color and proximity sensors

arduinotensorflowlitetutorials's Issues

what does it mean about 'Button connected to pin 3 and GND.'

hi, I am doing the emoji_button.ino project. I am confused about the 'Button connected to pin 3 and GND.'

Do I need to insert my Nano 33 BLE Sense board into the TinyShield? or use a jumper to connect Pin3 and GND? I am not sure. I will appreciate it if you could relpy.

TFLite on MKR1010 Wifi - Error from CMSIS

I tried to run the Sine-wave tutorial as well as the "magic-wand" example. Both error at the same point:
In file included from src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/Core/Include/cmsis_compiler.h:54:0, from src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_types.h:76, from src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math.h:199, from src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnsupportfunctions.h:33, from src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnfunctions.h:164, from src\tensorflow\lite\micro\kernels\cmsis-nn\conv.cpp:19: ArduinoData\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:58:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __enable_irq(void) ^~~~~~~~~~~~~~~ _ELIDABLE_INLINE

I'm using a MKR1010 WiFi module which runs Arm Cortex M0+. Any idea what it could be? It gets pretty far in the making from what I can tell. Since Sinewave doesn't use any specific board abilities (just serial out) I don't think it's related to that.

Normalizing sensor data

Hi @ALL ,

I just tried training a model for Punch/Flex gesture and was not able to understand why are we adding 4 and dividing by 8 similarly for 2000 and 4000 for gx values:

tensor += [
(df['aX'][index] + 4) / 8,
(df['aY'][index] + 4) / 8,
(df['aZ'][index] + 4) / 8,
(df['gX'][index] + 2000) / 4000,
(df['gY'][index] + 2000) / 4000,
(df['gZ'][index] + 2000) / 4000
]

If I capture my own custom data will these value change if yes then how we can feed in the right values for normalising the input tensor

Thanks

Not trainning the model

Hi!

I'm a beginner with TensorFlow and I'm currently trying to adapt your model to one that can sort falls.

My dataset consist in a 119 falls with 300 samples each, taken with an accelerometer with a range of +-16g and +-2000º (so I've changed te parameters given to normalize the dataset).

I get something like this every time I run the "Build & Train the Model" part on your code:

I made sure the data is formated correctly, so no empty spaces or more than one coma at a time...
[Fall_Arduino_100_g_short.txt]
(https://github.com/arduino/ArduinoTensorFlowLiteTutorials/files/4369122/Fall_Arduino_100_g_short.txt)

And I'm not sure what to do to make it work correctly...

Compilation error: tensorflow/lite/micro/kernels/micro_ops.h: No such file or directory

I am currently working with arduino nano 33 ble sense. Since the tensorflow lite library for arduino was removed, I manually installed using this link https://downloads.arduino.cc/libraries/github.com/bcmi-labs/Arduino_TensorFlowLite-1.15.0-ALPHA.zip?_gl=1*1yhwoez*_ga*NzU5Nzg3Mzg0LjE2NzUxNTU5MDk.*_ga_NEXN8H46L5*MTY3NTg4MDMwNi4xMC4xLjE2NzU4ODA0NjguMC4wLjA.

While trying to run my code I'm getting this error eventhough I have the files exactly in the path mentioned. The header files look like this

#include "TensorFlowLite.h"
#include "main_functions.h"
#include "tensorflow/lite/micro/kernels/micro_ops.h"
#include "tensorflow/lite/micro/micro_error_reporter.h"
#include "tensorflow/lite/micro/micro_interpreter.h"
#include "tensorflow/lite/micro/micro_mutable_op_resolver.h"
#include "tensorflow/lite/schema/schema_generated.h"
#include "tensorflow/lite/version.h"

Can someone please help me?

How can I add BLE to this code?

Hello. Thanks to you, I learned how to use tensorflow. And I added a count of gestures to this code. Now I'm going to send this number of counts to my smartphone via BLE.
However, when you add BLE code, it will be uploaded but the Bluetooth connection will not work.
This is the full code I wrote. I would really appreciate it if you could tell me the wrong thing.

#include <ArduinoBLE.h>
#include <Arduino_LSM9DS1.h> 
  
#include <TensorFlowLite.h>
#include <tensorflow/lite/experimental/micro/kernels/all_ops_resolver.h>
#include <tensorflow/lite/experimental/micro/micro_error_reporter.h>
#include <tensorflow/lite/experimental/micro/micro_interpreter.h>
#include <tensorflow/lite/schema/schema_generated.h>
#include <tensorflow/lite/version.h>

#include "model.h"

BLEService yscheulService("00001101-0000-1000-8000-00805F9B34FB"); 
BLEStringCharacteristic LevelChar("00002a11-0000-1000-8000-00805f9b34fb", BLERead | BLENotify,40);

const float accelerationThreshold = 2.5; // threshold of significant in G's
const int numSamples = 119;

int samplesRead = numSamples;

// global variables used for TensorFlow Lite (Micro)
tflite::MicroErrorReporter tflErrorReporter;

// pull in all the TFLM ops, you can remove this line and
// only pull in the TFLM ops you need, if would like to reduce
// the compiled size of the sketch.
tflite::ops::micro::AllOpsResolver tflOpsResolver;

const tflite::Model* tflModel = nullptr;
tflite::MicroInterpreter* tflInterpreter = nullptr;
TfLiteTensor* tflInputTensor = nullptr;
TfLiteTensor* tflOutputTensor = nullptr;

// Create a static memory buffer for TFLM, the size may need to
// be adjusted based on the model you are using
constexpr int tensorArenaSize = 8 * 1024;
byte tensorArena[tensorArenaSize];

// array to map gesture index to a name
const char* GESTURES[] = {"flex"};

#define NUM_GESTURES (sizeof(GESTURES) / sizeof(GESTURES[0]))

int count=0; // gesture count

//********************************************************************************************************************************

void setup() {
 Serial.begin(9600);
  if (!IMU.begin()) { //LSM9DS1센서 시작
    Serial.println("LSM9DS1 failed!!");
    while (1);
  }

  if (!BLE.begin()) {
    Serial.println("starting BLE failed!");
    while (1);
  }

  // print out the samples rates of the IMUs
  Serial.print("Accelerometer sample rate = ");
  Serial.print(IMU.accelerationSampleRate());
  Serial.println(" Hz");
  Serial.print("Gyroscope sample rate = ");
  Serial.print(IMU.gyroscopeSampleRate());
  Serial.println(" Hz");
  Serial.println();

  // get the TFL representation of the model byte array
  tflModel = tflite::GetModel(model);
  if (tflModel->version() != TFLITE_SCHEMA_VERSION) {
    Serial.println("Model schema mismatch!");
    while (1);
  }
  // Create an interpreter to run the model
  tflInterpreter = new tflite::MicroInterpreter(tflModel, tflOpsResolver, tensorArena, tensorArenaSize, &tflErrorReporter);
  
  // Allocate memory for the model's input and output tensors
  tflInterpreter->AllocateTensors();
  
  // Get pointers for the model's input and output tensors
  tflInputTensor = tflInterpreter->input(0);
  tflOutputTensor = tflInterpreter->output(0);

   // set advertised local name and service UUID:
  BLE.setAdvertisedService(yscheulService); // add the service UUID
  yscheulService.addCharacteristic(LevelChar);
  BLE.addService(yscheulService);
  // start advertising
  BLE.setLocalName("yschul");
  // start advertising
  BLE.advertise(); 
}
//********************************************************************************************************************************
String Level_String;
float aX, aY, aZ, gX, gY, gZ;

void updategyroLevel() {
//  if (IMU.accelerationAvailable()) {
//    IMU.readAcceleration(aX, aY, aX);
//    IMU.readGyroscope(gX, gY, gZ);
//    }
  Level_String=String(a); // count value -> BLE
  LevelChar.writeValue(Level_String);
  Serial.println(Level_String);
}
//********************************************************************************************************************************
void loop() {
  // wait for significant motion
  while (samplesRead == numSamples) {
    if (IMU.accelerationAvailable()) {
      // read the acceleration data
      IMU.readAcceleration(aX, aY, aZ);

      // sum up the absolutes
      float aSum = fabs(aX) + fabs(aY) + fabs(aZ);

      // check if it's above the threshold
      if (aSum >= accelerationThreshold) {
        // reset the sample read count
        samplesRead = 0;
        break;
      }
    }
  }
  // check if the all the required samples have been read since
  // the last time the significant motion was detected
  while (samplesRead < numSamples) {
    // check if new acceleration AND gyroscope data is available
    if (IMU.accelerationAvailable() && IMU.gyroscopeAvailable()) {
      // read the acceleration and gyroscope data
      IMU.readAcceleration(aX, aY, aZ);
      IMU.readGyroscope(gX, gY, gZ);

      // normalize the IMU data between 0 to 1 and store in the model's
      // input tensor
      tflInputTensor->data.f[samplesRead * 6 + 0] = (aX + 4.0) / 8.0;
      tflInputTensor->data.f[samplesRead * 6 + 1] = (aY + 4.0) / 8.0;
      tflInputTensor->data.f[samplesRead * 6 + 2] = (aZ + 4.0) / 8.0;
      tflInputTensor->data.f[samplesRead * 6 + 3] = (gX + 2000.0) / 4000.0;
      tflInputTensor->data.f[samplesRead * 6 + 4] = (gY + 2000.0) / 4000.0;
      tflInputTensor->data.f[samplesRead * 6 + 5] = (gZ + 2000.0) / 4000.0;

      samplesRead++;

      if (samplesRead == numSamples) {
        // Run inferencing
        TfLiteStatus invokeStatus = tflInterpreter->Invoke();
        if (invokeStatus != kTfLiteOk) {
          Serial.println("Invoke failed!");
          while (1);
          return;
        }

        // Loop through the output tensor values from the model
        Serial.print(GESTURES[0]); // GESTURES[0] = flex
        Serial.print(": ");
        Serial.println(tflOutputTensor->data.f[0], 6);       
        Serial.println();  
      }
    }
  }
// Counts when accuracy is 0.7 or higher
 if(tflOutputTensor->data.f[0] >= 0.7)
        {
          count=count+1;
          Serial.println(count);
        }
  
  // listen for BLE peripherals to connect:
  BLEDevice central = BLE.central();
  // if a central is connected to peripheral:
  if (central) {
    while (central.connected()) {
        updateyscheulLevel();
      }
    } 
}

TFLite MicroInterpreter() never returns on Arduino Nano BLE 33 Sense

I am trying out the gesture recognization example using the IMU_Classifier example for detecting a "punch" gesture.
I see that the Arduino setup() code is kind of blocked when trying to initialize a MicroInterpreter() instance as below.

// Create a static memory buffer for TFLM, the size may need to
// be adjusted based on the model you are using
constexpr int tensorArenaSize = 8 * 1024;

byte tensorArena[tensorArenaSize];

tfLiteInterpreter = new tflite::MicroInterpreter(tfLiteModel,tfLiteOpsResolver, tensorArena, tensorArenaSize, &tfLiteErrorReporter);

Could you please share if this could be due to model size or any other dependency not being met? I gave it a try by shrinking model layers to reduce the model size as below but I still see an issue. Here, I am only trying to classify the punch gesture.

`# build the model and train it
model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(16, activation='relu'))
model.add(tf.keras.layers.Dense(8, activation='relu'))
model.add(tf.keras.layers.Dense(NUM_GESTURES, activation='sigmoid')) # softmax is used, because we only expect one gesture to occur per input
model.compile(optimizer='rmsprop', loss='mse', metrics=['mae'])
history = model.fit(inputs_train, outputs_train, epochs=600, batch_size=1, validation_data=(inputs_validate, outputs_validate))
`

tensorflow/lite/experimental/micro/kernels/all_ops_resolver.h: No such file or directory

When I upload the IMU_Classifier to the Arduino nano 33 sense BLE I obtain this error:

tensorflow/lite/experimental/micro/kernels/all_ops_resolver.h: No such file or directory

I have the Arduino_Tensorflowlite library 2.1.0-Alpha precompiled installed..

Model Is Not Building

@lucach
@8bitkick
@sandeepmistry

Hi!

I have created the attached .csv files (currently .txt so I can upload to GitHub) for the punch and flex gestures and cannot get them to create a model. It seems to just generate nothing. Not sure what I am doing wrong?

punch.txt
flex.txt

error: 'AllOpsResolver' in namespace 'tflite::ops::micro' does not name a type tflite::ops::micro::AllOpsResolver tflOpsResolver;

When I upload the IMU_Classifier to the Arduino nano 33 sense BLE I obtain this error:

error: 'AllOpsResolver' in namespace 'tflite::ops::micro' does not name a type tflite::ops::micro::AllOpsResolver tflOpsResolver;

I have the Arduino_Tensorflowlite library 2.1.0-Alpha precompiled installed..

Increasing accuracy

@lucach
@8bitkick
@sandeepmistry

Thanks for doing this project, so cool!

I have got my Arduino to become quite accurate at recognizing two gestures but it still messes up occasionally. I have played around with training the model better, adjusting the G forces, and sample rate.

What would you guys suggest to increase its accuracy in recognizing gestures? Does it help to provide more example data when creating the model? Are their other variables you would experiment with?

Thanks!

Error compiling IMU_Classifier

After running and retrieving model.h from IMU_Capture .csv data, I can't compile IMU_Capture.ino. I can't find the problem
Here is the compilation error.

/home/apehooman/Arduino/libraries/Arduino_TensorFlowLite/src/cortex-m4/fpv4-sp-d16-softfp/libtensorflowlite.a(micro_error_reporter.cpp.o): In function `tflite::MicroErrorReporter::Report(char const*, std::__va_list)':
/home/arduino/workspace/Libraries-Google-Tensorflow-scraper/Arduino/libraries/tensorflow_lite_mirror/src/tensorflow/lite/micro/micro_error_reporter.cpp:35: undefined reference to `DebugLog'
/home/arduino/workspace/Libraries-Google-Tensorflow-scraper/Arduino/libraries/tensorflow_lite_mirror/src/tensorflow/lite/micro/micro_error_reporter.cpp:36: undefined reference to `DebugLog'
collect2: error: ld returned 1 exit status
Using library Arduino_LSM9DS1 at version 1.1.0 in folder: /home/apehooman/Arduino/libraries/Arduino_LSM9DS1 
Using library Wire in folder: /home/apehooman/.arduino15/packages/arduino/hardware/mbed/1.1.6/libraries/Wire (legacy)
Using library Arduino_TensorFlowLite at version 2.4.0-ALPHA-precompiled in folder: /home/apehooman/Arduino/libraries/Arduino_TensorFlowLite 

exit status 1
Error compiling for board Arduino Nano 33 BLE.

Tiny ML on Arduino: Gesture recognition tutorial results in a blank model.h

I attempted to run through the Tiny ML on Arduino: Gesture recognition example and it resulted in a a model.h file that is just a model array declaration.

Ex:

const unsigned char model[] = {
};

This is the example that I was following:
https://colab.research.google.com/github/arduino/ArduinoTensorFlowLiteTutorials/blob/master/GestureToEmoji/arduino_tinyml_workshop.ipynb#scrollTo=f92-4Hjy7kA8

The following Warnings were seen while running the example:
NOTE: An issue was filed with the Colab project but I do not see it listed.

Also, a gesture_model.tflite file was created and has about 145K of data.

• Setup Python Environment

E: Failed to fetch http://security.ubuntu.com/ubuntu/pool/main/v/vim/xxd_8.0.1453-1ubuntu1.1_amd64.deb  404  Not Found [IP: 91.189.88.152 80]
E: Unable to fetch some archives, maybe run apt-get update or try with --fix-missing?

• Build & Train the Model

Train on 12 samples, validate on 4 samples
Epoch 1/600
WARNING:tensorflow:Entity <function Function._initialize_uninitialized_variables.<locals>.initialize_variables at 0x7fe172912ae8> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: module 'gast' has no attribute 'Num'
WARNING: Entity <function Function._initialize_uninitialized_variables.<locals>.initialize_variables at 0x7fe172912ae8> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: module 'gast' has no attribute 'Num'
12/12 [==============================] - 1s 50ms/sample - loss: 0.3119 - mae: 0.5501 - val_loss: 0.2502 - val_mae: 0.4998
Epoch 2/600
12/12 [==============================] - 0s 3ms/sample - loss: 0.2653 - mae: 0.5116 - val_loss: 0.2498 - val_mae: 0.4994
Epoch 3/600
12/12 [==============================] - 0s 3ms/sample - loss: 0.2620 - mae: 0.5116 - val_loss: 0.2493 - val_mae: 0.4991
Epoch 4/600
12/12 [==============================] - 0s 3ms/sample - loss: 0.2628 - mae: 0.5082 - val_loss: 0.2488 - val_mae: 0.4985
Epoch 5/600
12/12 [==============================] - 0s 3ms/sample - loss: 0.2569 - mae: 0.5058 - val_loss: 0.2443 - val_mae: 0.4942
Epoch 6/600
12/12 [==============================] - 0s 3ms/sample - loss: 0.2553 - mae: 0.4992 - val_loss: 0.2579 - val_mae: 0.4993
Epoch 7/600
12/12 [==============================] - 0s 3ms/sample - loss: 0.2619 - mae: 0.5072 - val_loss: 0.2531 - val_mae: 0.4989
Epoch 8/600
12/12 [==============================] - 0s 3ms/sample - loss: 0.2576 - mae: 0.5051 - val_loss: 0.2521 - val_mae: 0.4983
Epoch 9/600
12/12 [==============================] - 0s 3ms/sample - loss: 0.2569 - mae: 0.5049 - val_loss: 0.2499 - val_mae: 0.4981
Epoch 10/600
12/12 [==============================] - 0s 3ms/sample - loss: 0.2544 - mae: 0.5036 - val_loss: 0.2491 - val_mae: 0.4979
Epoch 11/600
12/12 [==============================] - 0s 3ms/sample - loss: 0.2533 - mae: 0.5029 - val_loss: 0.2485 - val_mae: 0.4978

• Run with Test Data

/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:10: MatplotlibDeprecationWarning: cycling among columns of inputs with non-matching shapes is deprecated.
  # Remove the CWD from sys.path while we load stuff.
/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:11: MatplotlibDeprecationWarning: cycling among columns of inputs with non-matching shapes is deprecated.
  # This is added back by InteractiveShellApp.init_path()

• Convert the Trained Model to Tensor Flow Lite

WARNING:tensorflow:Entity <function Function._initialize_uninitialized_variables.<locals>.initialize_variables at 0x7fe16a17d598> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: module 'gast' has no attribute 'Num'
WARNING: Entity <function Function._initialize_uninitialized_variables.<locals>.initialize_variables at 0x7fe16a17d598> could not be transformed and will be executed as-is. Please report this to the AutoGraph team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output. Cause: module 'gast' has no attribute 'Num'
Model is 147764 bytes

xx bytes lost due to alignment. To avoid this loss, please make sure the tensor_arena is 16 bytes aligned

I get this error message I get when I basically replicate the gesture recognition tutorial in Arduino ML guide.

More importantly, though the arduino sketch builds, the model doesn't appear to be working, since the serial output doesn't report any gestures.

The workaround that worked for me was to change the header in the model.h encoding in the Google Colab ML notebook:

Original: !echo "const unsigned char model[] = {"

What worked for me: !echo "alignas(8)const unsigned char model[] = {"

The addition of alignas(8) fixed the issue in that the arduino sketch build is now working, and I am able to classify gestures.

fatal error: cstdint: No such file or directory

I tried to compile the program on the Arduino nano but got the error shown as follows:

Arduino: 1.8.9 (Windows 10), Board: "Arduino Nano, ATmega328P"

Build options changed, rebuilding all
In file included from C:\Users\neoya\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/experimental/micro/micro_error_reporter.h:21:0,

                 from D:\Phenoma\Gesture Detection\Gesture-Recognition-master\adafruit\sketch_nov08a\sketch_nov08a.ino:19:

C:\Users\neoya\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/experimental/micro/debug_log_numbers.h:18:19: fatal error: cstdint: No such file or directory

compilation terminated.

exit status 1
Error compiling for board Arduino Nano.

This report would have more information with
"Show verbose output during compilation"
option enabled in File -> Preferences.

From the error, I guess the error is related to C++ 11 but don't know how to solve it. Do you have any suggestion?

Thanks!

micro_mutable_op_resolver.h:21:10: fatal error: tensorflow/lite/c/common.h: No such file or directory

Tensorflow version : '2.1.0'
Target platform: Arduino nano 33 sense BLE

micro_mutable_op_resolver.h:21:10: fatal error: tensorflow/lite/c/common.h: No such file or directory

when I deploy hello world model to edge I got above error. Following contains the headers of the test run

#include "tensorflow/lite/micro/examples/hello_world/model.h"
#include "tensorflow/lite/micro/all_ops_resolver.h"
#include "tensorflow/lite/micro/micro_error_reporter.h"
#include "tensorflow/lite/micro/micro_interpreter.h"
#include "tensorflow/lite/micro/testing/micro_test.h"
#include "tensorflow/lite/schema/schema_generated.h"
#include "tensorflow/lite/version.h"

undefined reference to `DebugLog' in micro_error_reporter.cpp

I am working with Arduino_TensorFlowLite-2.4.0-ALPHA-precompiled library and trying to compile my arduino sketch. But I keep getting this error Library Arduino_TensorFlowLite has been declared precompiled: Using precompiled library in C:\Users\prane\Documents\Arduino\libraries\Arduino_TensorFlowLite-2.4.0-ALPHA-precompiled\src\cortex-m4\fpv4-sp-d16-softfp C:\Users\prane\Documents\Arduino\libraries\Arduino_TensorFlowLite-2.4.0-ALPHA-precompiled\src\cortex-m4\fpv4-sp-d16-softfp\libtensorflowlite.a(micro_error_reporter.cpp.o): In function tflite::MicroErrorReporter::Report(char const*, std::__va_list)':
/home/arduino/workspace/Libraries-Google-Tensorflow-scraper/Arduino/libraries/tensorflow_lite_mirror/src/tensorflow/lite/micro/micro_error_reporter.cpp:35: undefined reference to DebugLog' /home/arduino/workspace/Libraries-Google-Tensorflow-scraper/Arduino/libraries/tensorflow_lite_mirror/src/tensorflow/lite/micro/micro_error_reporter.cpp:36: undefined reference to DebugLog'
collect2.exe: error: ld returned 1 exit status

exit status 1

Compilation error: exit status 1`

I've included my sketch below. Any help would be greatly helpful. Thanks

`#include "TensorFlowLite.h"
#include "tensorflow/lite/micro/all_ops_resolver.h"
#include "tensorflow/lite/micro/micro_error_reporter.h"
#include "tensorflow/lite/micro/micro_interpreter.h"
//#include "tensorflow/lite/micro/system_setup.h"
#include "tensorflow/lite/schema/schema_generated.h"
#include "tensorflow/lite/version.h"
#include "image_data.h"
#include "model_data.h"

const int kInputTensorSize = 1 * 28 * 28 * 1;
const int kNumClasses = 10;
namespace{
tflite::ErrorReporter* error_reporter = nullptr;
const tflite::Model* model = nullptr;
tflite::MicroInterpreter* interpreter = nullptr;
TfLiteTensor* input = nullptr;
TfLiteTensor* output = nullptr;
int inference_count = 0;

constexpr int kTensorArenaSize = 2*1024;
uint8_t tensor_arena[kTensorArenaSize];
}

void setup() {
Serial.begin(115200);
// tflite::InitializeTarget();
// memset(tensor_arena, 0, kTensorArenaSize*sizeof(uint8_t));

// Set up logging.
static tflite::MicroErrorReporter micro_error_reporter;
error_reporter = &micro_error_reporter;

model = tflite::GetModel(model_data);
if (model->version() != TFLITE_SCHEMA_VERSION) {
Serial.println("Model provided is schema version "
+ String(model->version()) + " not equal "
+ "to supported version "
+ String(TFLITE_SCHEMA_VERSION));
return;
} else {
Serial.println("Model version: " + String(model->version()));
}

// This pulls in all the operation implementations we need.
static tflite::AllOpsResolver resolver;

// Build an interpreter to run the model with.
static tflite::MicroInterpreter static_interpreter(
model, resolver, tensor_arena, kTensorArenaSize, error_reporter);
interpreter = &static_interpreter;

// Build an interpreter to run the model with.
// tflite::MicroInterpreter* static_interpreter_ptr = new tflite::MicroInterpreter(
// model, resolver, tensor_arena, kTensorArenaSize, error_reporter);
// interpreter = static_interpreter_ptr;

// Allocate memory from the tensor_arena for the model's tensors.
TfLiteStatus allocate_status = interpreter->AllocateTensors();
if (allocate_status != kTfLiteOk) {
Serial.println("AllocateTensors() failed");
return;
} else {
Serial.println("AllocateTensor() Success");
}

size_t used_size = interpreter->arena_used_bytes();
Serial.println("Area used bytes: " + String(used_size));
input = interpreter->input(0);
output = interpreter->output(0);

/* check input */
if (input->type != kTfLiteFloat32) {
Serial.println("input type mismatch. expected input type is float32");
return;
} else {
Serial.println("input type is float32");
}

Serial.println("Model input:");
Serial.println("input->type: " + String(input->type));
Serial.println("dims->size: " + String(input->dims->size));
for (int n = 0; n < input->dims->size; ++n) {
Serial.println("dims->data[n]: " + String(input->dims->data[n]));
}

Serial.println("Model output:");
Serial.println("dims->size: " + String(output->dims->size));
for (int n = 0; n < output->dims->size; ++n) {
Serial.println("dims->data[n]: " + String(output->dims->data[n]));
}

}
void loop() {

// Define the input image array
const uint8_t* kImageDataPtr = kImageData; // Pointer to start of image data
uint8_t input_image[kInputTensorSize];
for (int i = 0; i < kInputTensorSize; i++) {
input_image[i] = *(kImageDataPtr++);
}

for(int i=0; i<kInputTensorSize; i++){
input->data.f[i] = (float)input_image[i] / 255.0;
}

// Run inference
interpreter->Invoke();

// Print the predicted class
int predicted_class = -1;
float max_score = -1;
for (int i = 0; i < kNumClasses; i++) {
float score = output->data.f[i];
if (score > max_score) {
predicted_class = i;
max_score = score;
}
}
Serial.println(predicted_class);

}`

Breakage caused by removal of "Arduino_TensorFlowLite" library from Library Manager

The "Arduino_TensorFlowLite" library dependency of these tutorials was removed from Library Manager at the request of the TensorFlow Lite Micro maintainers (arduino/library-registry#1748).

That removal impacts this project in several ways:

Documentation

The installation instructions specify installation of the library from Library Manager:

https://github.com/arduino/ArduinoTensorFlowLiteTutorials/blob/master/GestureToEmoji/exercises/exercise1.md#arduino-libraries

Install the following Arduino libraries using the Library manager:

• TensorFlow Lite library (search for "Arduino_TensorFlowLite")

This is no longer possible.

TensorFlow's library must be installed manually. The library's documentation provides instructions:

https://github.com/tensorflow/tflite-micro-arduino-examples#how-to-install

Code

TensorFlow's library does not contain the file tensorflow/lite/version.h, so the code that contains an #include directive for this header no longer compiles:

home/runner/work/ArduinoTensorFlowLiteTutorials/ArduinoTensorFlowLiteTutorials/GestureToEmoji/ArduinoSketches/IMU_Classifier/IMU_Classifier.ino:28:10: fatal error: tensorflow/lite/version.h: No such file or directory
   #include <tensorflow/lite/version.h>
            ^~~~~~~~~~~~~~~~~~~~~~~~~~~
  compilation terminated.

CI

The repository contains a GitHub Actions workflow that provides a "smoke test" on relevant changes to the project by compiling the sketches:

https://github.com/arduino/ArduinoTensorFlowLiteTutorials/blob/master/.github/workflows/compile-sketches.yml

The workflow is configured to install the dependency from Library Manager, which now fails:

Running command: /home/runner/bin/arduino-cli lib install Arduino_TensorFlowLite 
   Error installing Arduino_TensorFlowLite: Library 'Arduino_TensorFlowLite' not found

Looking for someone to understand 2 ou 3 things :-)

I already push that issue here ==> robmarkcole/arduino-tensorflow-example#1

Hello,

I try the tensorflow example, and i have some issues / or things that i don't understand.

First i use your csv files (i m talking about robmarkcole files); it generates very beautiful graphics for errors, etc... but when I change the seed, graphics (so errors evaluation...) are not so nice, and very different. i m ok for different, but ...

So after i try to generate my own csv files for punch and flex gestures; the results are very bad (loss).

For the classification part; the training model with your files is not working very well, with my files it's worse.

Maybe there's something i miss somewhere.

It don't where to exchange about this, i try with you

Thx

Tinyml Workshop Runtime Error

Running through the tutorial: Nano 33 BLE Sense Rev2
Get Started With Machine Learning on Arduino

In arduino_tinyml_workshop.ipynb in Colab
Got data and uploaded to Colab.
Running the cells, got to the cell: Run with Test Data'
Runtime errors on these lines:
plt.plot(inputs_test, outputs_test, 'b.', label='Actual')
plt.plot(inputs_test, predictions, 'r.', label='Predicted')

Added in a few prints of data...

OUTPUT WITH ERRORS:
1/1 [==============================] - 0s 39ms/step
predictions =
[[1. 0. ]
[0.998 0.002]
[0. 1. ]
[1. 0. ]]
inputs_test =
[[0.701375 0.520875 0.378875 ... 0.500183 0.499817 0.499878 ]
[0.5895 0.461625 0.743125 ... 0.500534 0.50016775 0.50004575]
[0.68425 0.4585 0.71725 ... 0.4999695 0.4987335 0.49971 ]
[0.66625 0.51975 0.3385 ... 0.500885 0.500702 0.5009155 ]]
actual =
[[1. 0.]
[1. 0.]
[0. 1.]
[1. 0.]]

ValueError Traceback (most recent call last)
in <cell line: 12>()
10 plt.clf()
11 plt.title('Training data predicted vs actual values')
---> 12 plt.plot(inputs_test, outputs_test, 'b.', label='Actual')
13 plt.plot(inputs_test, predictions, 'r.', label='Predicted')
14 plt.show()

3 frames
/usr/local/lib/python3.10/dist-packages/matplotlib/axes/_base.py in _plot_args(self, tup, kwargs, return_kwargs, ambiguous_fmt_datakey)
520 ncx, ncy = x.shape[1], y.shape[1]
521 if ncx > 1 and ncy > 1 and ncx != ncy:
--> 522 raise ValueError(f"x has {ncx} columns but y has {ncy} columns")
523 if ncx == 0 or ncy == 0:
524 return []

ValueError: x has 714 columns but y has 2 columns

no matching function for call to tflite::MicroInterpreter

In file included from /Users/ballball/Documents/Arduino/libraries/Arduino_TensorFlowLite/src/tensorflow/lite/micro/micro_error_reporter.h:19:0,
from /Users/ballball/Documents/Arduino/gesture/IMU_Classifier/IMU_Classifier.ino:25:
/Users/ballball/Documents/Arduino/libraries/Arduino_TensorFlowLite/src/tensorflow/lite/experimental/micro/compatibility.h:29:0: warning: "TF_LITE_REMOVE_VIRTUAL_DELETE" redefined
#define TF_LITE_REMOVE_VIRTUAL_DELETE

In file included from /Users/ballball/Documents/Arduino/libraries/Arduino_TensorFlowLite/src/tensorflow/lite/micro/all_ops_resolver.h:18:0,
from /Users/ballball/Documents/Arduino/gesture/IMU_Classifier/IMU_Classifier.ino:24:
/Users/ballball/Documents/Arduino/libraries/Arduino_TensorFlowLite/src/tensorflow/lite/micro/compatibility.h:26:0: note: this is the location of the previous definition
#define TF_LITE_REMOVE_VIRTUAL_DELETE \

/Users/ballball/Documents/Arduino/gesture/IMU_Classifier/IMU_Classifier.ino: In function 'void setup()':
/Users/ballball/Documents/Arduino/gesture/IMU_Classifier/IMU_Classifier.ino:91:122: error: no matching function for call to 'tflite::MicroInterpreter::MicroInterpreter(const tflite::Model*&, tflite::AllOpsResolver&, byte [8192], const int&, tflite::MicroErrorReporter*)'
tflInterpreter = new tflite::MicroInterpreter(tflModel, tflOpsResolver, tensorArena, tensorArenaSize, &tflErrorReporter);
^
In file included from /Users/ballball/Documents/Arduino/gesture/IMU_Classifier/IMU_Classifier.ino:26:0:
/Users/ballball/Documents/Arduino/libraries/Arduino_TensorFlowLite/src/tensorflow/lite/micro/micro_interpreter.h:60:3: note: candidate: tflite::MicroInterpreter::MicroInterpreter(const tflite::Model*, const tflite::MicroOpResolver&, tflite::MicroAllocator*, tflite::MicroResourceVariables*, tflite::MicroProfilerInterface*)
MicroInterpreter(const Model* model, const MicroOpResolver& op_resolver,
^~~~~~~~~~~~~~~~
/Users/ballball/Documents/Arduino/libraries/Arduino_TensorFlowLite/src/tensorflow/lite/micro/micro_interpreter.h:60:3: note: no known conversion for argument 3 from 'byte [8192] {aka unsigned char [8192]}' to 'tflite::MicroAllocator*'
/Users/ballball/Documents/Arduino/libraries/Arduino_TensorFlowLite/src/tensorflow/lite/micro/micro_interpreter.h:50:3: note: candidate: tflite::MicroInterpreter::MicroInterpreter(const tflite::Model*, const tflite::MicroOpResolver&, uint8_t*, size_t, tflite::MicroResourceVariables*, tflite::MicroProfilerInterface*)
MicroInterpreter(const Model* model, const MicroOpResolver& op_resolver,
^~~~~~~~~~~~~~~~
/Users/ballball/Documents/Arduino/libraries/Arduino_TensorFlowLite/src/tensorflow/lite/micro/micro_interpreter.h:50:3: note: no known conversion for argument 5 from 'tflite::MicroErrorReporter*' to 'tflite::MicroResourceVariables*'
/Users/ballball/Documents/Arduino/libraries/Arduino_TensorFlowLite/src/tensorflow/lite/micro/micro_interpreter.h:40:7: note: candidate: constexpr tflite::MicroInterpreter::MicroInterpreter(const tflite::MicroInterpreter&)
class MicroInterpreter {
^~~~~~~~~~~~~~~~
/Users/ballball/Documents/Arduino/libraries/Arduino_TensorFlowLite/src/tensorflow/lite/micro/micro_interpreter.h:40:7: note: candidate expects 1 argument, 5 provided
/Users/ballball/Documents/Arduino/gesture/IMU_Classifier/IMU_Classifier.ino: In function 'void loop()':
/Users/ballball/Documents/Arduino/gesture/IMU_Classifier/IMU_Classifier.ino:152:27: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (int i = 0; i < NUM_GESTURES; i++) {

exit status 1

Compilation error: no matching function for call to 'tflite::MicroInterpreter::MicroInterpreter(const tflite::Model*&, tflite::AllOpsResolver&, byte [8192], const int&, tflite::MicroErrorReporter*)'

COM stuck after uploading IMU Classifier sketch？

New to Arduino, I follow with the Arduino TensorFlow Lite Tutorials and trained "GestureToEmoji" IMU Classifier model, which is deployed on BLE. It worked well previously, yet its stuck a serial monitor these day, after upload sketch to the board. Where I can figure out more information about it?

GestureToEmoji: Exercise 6

No official Repository of Library

Hi,
I am applying to Arduino this season of GSoC 2020. So, I would like to contribute to the Arduino_TensorFlowLite libarry, but I fail to find the upstream on GitHub. Can you please tell me the reason behind that ?

KeyError Traceback (most recent call last) /usr/local/lib/python3.6/dist-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)

When running the Graph Data (optional) code I get the following error message:

"KeyError Traceback (most recent call last) /usr/local/lib/python3.6/dist-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)"

I get the same message also when running the Parse and prepare the data code.

I believe that I have successfully completed the previous steps in the workbook (setting up the Pyrhon Environment runs OK and I have also uploaded the the flex.csv and punch.csv files to the main folder and also to the sample_data folder).

I was wondering that am I doing something wrong or is there a workaround for the problem?

Plot of predictions with test data in Colab notebook doesn't make much sense

In the Colab notebook, after the training we plot some graphs.
The last one, which is "Plot the predictions along with to the test data", is literally taken from a standard TensorFlow Lite example notebook (see https://colab.research.google.com/github/tensorflow/tensorflow/blob/master/tensorflow/lite/experimental/micro/examples/hello_world/create_sine_model.ipynb#scrollTo=L_vE-ZDkHVxe )
but does not make much sense in this context.

Besides that, the code for that plot currently (ab)uses a deprecated matplotlib behaviour

/usr/local/lib/python3.6/dist-packages/matplotlib/axes/_base.py:380: MatplotlibDeprecationWarning: 
cycling among columns of inputs with non-matching shapes is deprecated.

which also suggests that the current plot is a bit nonsensical.

Error when compiling in nRF52 Arduino interface

Hi,

Thank you for providing this great tutorial. I tried to implement this project on adafruit bluefruit nRF52 but get an error during the compilation. the link below is the model.h and .ino file I used and error details shown in readme file.
https://github.com/yang12313/tensorflow_lite_nRF52.
Could you help me fix this issue. Thank you so much.

Best,

HY

it can be apply to nano 33 iot?

hello!
i'm try to apply this code form nano 33 iot.
imu capture just change header name just 1->3

but imu classficate apear this error what the problem or just it is not support nano33iot imu sensor?

my eeror page like this

아두이노:1.8.15 (Windows 10), 보드:"Arduino NANO 33 IoT"

Library Arduino_TensorFlowLite has been declared precompiled:Precompiled library in "C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src\cortex-m0plus" not foundIn file included from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/Core/Include/cmsis_compiler.h:54:0,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_types.h:76,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math.h:199,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnsupportfunctions.h:33,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnfunctions.h:164,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src\tensorflow\lite\micro\kernels\cmsis-nn\fully_connected.cpp:18:C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:58:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __enable_irq(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:69:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __disable_irq(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:80:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_CONTROL(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEIn file included from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/Core/Include/cmsis_compiler.h:54:0,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_types.h:76,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math.h:199,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnsupportfunctions.h:33,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnfunctions.h:164,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src\tensorflow\lite\micro\kernels\cmsis-nn\conv.cpp:19:C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:58:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __enable_irq(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:94:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_CONTROL(uint32_t control)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:69:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __disable_irq(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:105:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_IPSR(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:119:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_APSR(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:134:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_xPSR(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:148:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_PSP(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:162:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_PSP(uint32_t topOfProcStack)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:173:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_MSP(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:188:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_MSP(uint32_t topOfMainStack)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:199:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_PRIMASK(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:213:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_PRIMASK(uint32_t priMask)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:373:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __NOP(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:80:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_CONTROL(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:383:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __WFI(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:394:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __WFE(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:94:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_CONTROL(uint32_t control)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:404:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __SEV(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:105:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_IPSR(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:416:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __ISB(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:119:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_APSR(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:427:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __DSB(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:134:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_xPSR(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:438:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __DMB(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:148:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_PSP(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:450:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE uint32_t __REV(uint32_t value)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:469:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE uint32_t __REV16(uint32_t value)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:162:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_PSP(uint32_t topOfProcStack)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:484:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE int32_t __REVSH(int32_t value)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEIn file included from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/Core/Include/cmsis_compiler.h:54:0,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_types.h:76,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math.h:199,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnsupportfunctions.h:33,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnfunctions.h:164,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src\tensorflow\lite\micro\kernels\cmsis-nn\depthwise_conv.cpp:18:C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:58:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __enable_irq(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:173:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_MSP(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:69:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __disable_irq(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:188:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_MSP(uint32_t topOfMainStack)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:80:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_CONTROL(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:199:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_PRIMASK(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:504:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE uint32_t __ROR(uint32_t op1, uint32_t op2)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:213:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_PRIMASK(uint32_t priMask)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:526:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE uint32_t __RBIT(uint32_t value)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:373:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __NOP(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:383:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __WFI(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEIn file included from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math.h:200:0,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnsupportfunctions.h:33,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnfunctions.h:164,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src\tensorflow\lite\micro\kernels\cmsis-nn\fully_connected.cpp:18:C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:75:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE q31_t read_q15x2 ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:394:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __WFE(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:404:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __SEV(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:94:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE q31_t read_q15x2_ia ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:416:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __ISB(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:114:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE q31_t read_q15x2_da ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:427:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __DSB(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:94:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_CONTROL(uint32_t control)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:135:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE void write_q15x2_ia ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:438:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __DMB(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:105:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_IPSR(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:450:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE uint32_t __REV(uint32_t value)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:156:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE void write_q15x2 ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:469:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE uint32_t __REV16(uint32_t value)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:484:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE int32_t __REVSH(int32_t value)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:176:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE q31_t read_q7x4_ia ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:504:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE uint32_t __ROR(uint32_t op1, uint32_t op2)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:119:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_APSR(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:526:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE uint32_t __RBIT(uint32_t value)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:198:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE q31_t read_q7x4_da ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:134:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_xPSR(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:148:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_PSP(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEIn file included from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math.h:200:0,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnsupportfunctions.h:33,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnfunctions.h:164,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src\tensorflow\lite\micro\kernels\cmsis-nn\conv.cpp:19:C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:75:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE q31_t read_q15x2 ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:218:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE void write_q7x4_ia ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:162:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_PSP(uint32_t topOfProcStack)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:94:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE q31_t read_q15x2_ia ( ^~~~~~~~~~~~~~~~~~~~In file included from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math.h:202:0,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnsupportfunctions.h:33,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnfunctions.h:164,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src\tensorflow\lite\micro\kernels\cmsis-nn\fully_connected.cpp:18:C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:136:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE q31_t clip_q63_to_q31(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:173:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_MSP(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:114:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE q31_t read_q15x2_da ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:146:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE q15_t clip_q63_to_q15(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:188:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_MSP(uint32_t topOfMainStack)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:135:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE void write_q15x2_ia ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:156:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE q7_t clip_q31_to_q7(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:199:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_PRIMASK(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:156:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE void write_q15x2 ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:213:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_PRIMASK(uint32_t priMask)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:166:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE q15_t clip_q31_to_q15(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:176:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE q31_t read_q7x4_ia ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:198:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE q31_t read_q7x4_da ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:218:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE void write_q7x4_ia ( ^~~~~~~~~~~~~~~~~~~~In file included from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math.h:202:0,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnsupportfunctions.h:33,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnfunctions.h:164,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src\tensorflow\lite\micro\kernels\cmsis-nn\conv.cpp:19:C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:136:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE q31_t clip_q63_to_q31(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:373:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __NOP(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:146:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE q15_t clip_q63_to_q15(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:383:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __WFI(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:156:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE q7_t clip_q31_to_q7(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:166:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE q15_t clip_q31_to_q15(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:394:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __WFE(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:176:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE q63_t mult32x64(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:245:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __QADD8(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:404:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __SEV(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:263:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __QSUB8(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:281:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __QADD16(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:176:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE q63_t mult32x64(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:416:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __ISB(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:245:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __QADD8(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:298:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SHADD16(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:427:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __DSB(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:438:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __DMB(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:314:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __QSUB16(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:450:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE uint32_t __REV(uint32_t value)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:330:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SHSUB16(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:469:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE uint32_t __REV16(uint32_t value)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:484:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE int32_t __REVSH(int32_t value)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:346:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __QASX(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:504:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE uint32_t __ROR(uint32_t op1, uint32_t op2)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:362:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SHASX(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:526:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE uint32_t __RBIT(uint32_t value)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEIn file included from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math.h:200:0,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnsupportfunctions.h:33,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnfunctions.h:164,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src\tensorflow\lite\micro\kernels\cmsis-nn\depthwise_conv.cpp:18:C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:75:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE q31_t read_q15x2 ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:263:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __QSUB8(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:378:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __QSAX(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:281:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __QADD16(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:394:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SHSAX(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:410:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SMUSDX(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:421:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SMUADX(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:433:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE int32_t __QADD(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:444:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE int32_t __QSUB(   ^~~~~~~~~~~~~~~~~~~~In file included from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/Core/Include/cmsis_compiler.h:54:0,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_types.h:76,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math.h:199,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnsupportfunctions.h:33,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnfunctions.h:164,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src\tensorflow\lite\micro\kernels\cmsis-nn\pooling.cpp:17:C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:58:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __enable_irq(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:455:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SMLAD(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:69:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __disable_irq(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:94:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE q31_t read_q15x2_ia ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:469:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SMLADX(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:80:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_CONTROL(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:298:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SHADD16(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:483:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SMLSDX(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:114:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE q31_t read_q15x2_da ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:94:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_CONTROL(uint32_t control)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:497:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint64_t __SMLALD(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:135:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE void write_q15x2_ia ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:105:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_IPSR(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:512:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint64_t __SMLALDX(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:156:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE void write_q15x2 ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:314:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __QSUB16(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:119:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_APSR(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:527:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SMUAD(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:330:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SHSUB16(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:134:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_xPSR(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:539:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SMUSD(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:346:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __QASX(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:148:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_PSP(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:551:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SXTB16(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:162:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_PSP(uint32_t topOfProcStack)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:362:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SHASX(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:176:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE q31_t read_q7x4_ia ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:561:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE int32_t __SMMLA(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:173:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_MSP(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:198:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE q31_t read_q7x4_da ( ^~~~~~~~~~~~~~~~~~~~In file included from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math.h:203:0,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnsupportfunctions.h:33,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnfunctions.h:164,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src\tensorflow\lite\micro\kernels\cmsis-nn\conv.cpp:19:C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/utils.h:50:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t arm_recip_q31(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:188:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_MSP(uint32_t topOfMainStack)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math_memory.h:218:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE void write_q7x4_ia ( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/utils.h:101:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t arm_recip_q15(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/utils.h:155:1: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __STATIC_INLINE  void arm_norm_64_to_32u(uint64_t in, int32_t * normalized, int32_t *norm) ^~~~~~~~~~~~~~~ _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:199:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __get_PRIMASK(void)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/utils.h:207:1: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __STATIC_INLINE q31_t arm_div_q63_to_q31(q63_t num, q31_t den) ^~~~~~~~~~~~~~~ _ELIDABLE_INLINEC:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:213:36: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__( ( always_inline ) ) __STATIC_INLINE void __set_PRIMASK(uint32_t priMask)                                    ^~~~~~~~~~~~~~~                                    _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:378:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __QSAX(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:373:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __NOP(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEIn file included from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/statistics_functions.h:36:0,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/bayes_functions.h:35,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math.h:207,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnsupportfunctions.h:33,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnfunctions.h:164,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src\tensorflow\lite\micro\kernels\cmsis-nn\conv.cpp:19:C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/fast_math_functions.h:196:1: error: '__STATIC_FORCEINLINE' does not name a type __STATIC_FORCEINLINE arm_status arm_sqrt_f32( ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:394:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SHSAX(   ^~~~~~~~~~~~~~~~~~~~In file included from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math.h:202:0,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnsupportfunctions.h:33,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnfunctions.h:164,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src\tensorflow\lite\micro\kernels\cmsis-nn\depthwise_conv.cpp:18:C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:136:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE q31_t clip_q63_to_q31(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:410:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SMUSDX(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:146:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE q15_t clip_q63_to_q15(   ^~~~~~~~~~~~~~~~~~~~In file included from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math.h:211:0,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnsupportfunctions.h:33,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnfunctions.h:164,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src\tensorflow\lite\micro\kernels\cmsis-nn\conv.cpp:19:C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/controller_functions.h:268:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE float32_t arm_pid_f32(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\AppData\Local\Arduino15\packages\arduino\tools\CMSIS\4.5.0/CMSIS/Include/cmsis_gcc.h:383:32: error: '__STATIC_INLINE' does not name a type; did you mean '_ELIDABLE_INLINE'? __attribute__((always_inline)) __STATIC_INLINE void __WFI(void)                                ^~~~~~~~~~~~~~~                                _ELIDABLE_INLINEC:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:421:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE uint32_t __SMUADX(   ^~~~~~~~~~~~~~~~~~~~C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/dsp/none.h:156:3: error: '__STATIC_FORCEINLINE' does not name a type   __STATIC_FORCEINLINE q7_t clip_q31_to_q7(   ^~~~~~~~~~~~~~~~~~~~In file included from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/DSP/Include/arm_math.h:211:0,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite/micro/tools/make/downloads/cmsis/CMSIS/NN/Include/arm_nnsupportfunctions.h:33,                 from C:\Users\ksh26\Documents\Arduino\libraries\Arduino_TensorFlowLite\src/tensorflow/lite