Hello all, I am attempting to run a simple object detection program created through Edge Impulse on an ESP32-CAM module using the exact steps included in the Dronebot Workshop tutorial on simple object detection with the ESP32 CAM. This is the Tiny ML Code obtained from Edge Impulse:
/* Edge Impulse Arduino examples
* Copyright (c) 2022 EdgeImpulse Inc.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
// These sketches are tested with 2.0.4 ESP32 Arduino Core
// https://github.com/espressif/arduino-esp32/releases/tag/2.0.4
/* Includes ---------------------------------------------------------------- */
#include <Bill_detector_inferencing.h>
#include "edge-impulse-sdk/dsp/image/image.hpp"
#include "esp_camera.h"
// Select camera model - find more camera models in camera_pins.h file here
// https://github.com/espressif/arduino-esp32/blob/master/libraries/ESP32/examples/Camera/CameraWebServer/camera_pins.h
//#define CAMERA_MODEL_ESP_EYE // Has PSRAM
#define CAMERA_MODEL_AI_THINKER // Has PSRAM
#if defined(CAMERA_MODEL_ESP_EYE)
#define PWDN_GPIO_NUM -1
#define RESET_GPIO_NUM -1
#define XCLK_GPIO_NUM 4
#define SIOD_GPIO_NUM 18
#define SIOC_GPIO_NUM 23
#define Y9_GPIO_NUM 36
#define Y8_GPIO_NUM 37
#define Y7_GPIO_NUM 38
#define Y6_GPIO_NUM 39
#define Y5_GPIO_NUM 35
#define Y4_GPIO_NUM 14
#define Y3_GPIO_NUM 13
#define Y2_GPIO_NUM 34
#define VSYNC_GPIO_NUM 5
#define HREF_GPIO_NUM 27
#define PCLK_GPIO_NUM 25
#elif defined(CAMERA_MODEL_AI_THINKER)
#define PWDN_GPIO_NUM 32
#define RESET_GPIO_NUM -1
#define XCLK_GPIO_NUM 0
#define SIOD_GPIO_NUM 26
#define SIOC_GPIO_NUM 27
#define Y9_GPIO_NUM 35
#define Y8_GPIO_NUM 34
#define Y7_GPIO_NUM 39
#define Y6_GPIO_NUM 36
#define Y5_GPIO_NUM 21
#define Y4_GPIO_NUM 19
#define Y3_GPIO_NUM 18
#define Y2_GPIO_NUM 5
#define VSYNC_GPIO_NUM 25
#define HREF_GPIO_NUM 23
#define PCLK_GPIO_NUM 22
#else
#error "Camera model not selected"
#endif
/* Constant defines -------------------------------------------------------- */
#define EI_CAMERA_RAW_FRAME_BUFFER_COLS 320
#define EI_CAMERA_RAW_FRAME_BUFFER_ROWS 240
#define EI_CAMERA_FRAME_BYTE_SIZE 3
/* Private variables ------------------------------------------------------- */
static bool debug_nn = false; // Set this to true to see e.g. features generated from the raw signal
static bool is_initialised = false;
uint8_t *snapshot_buf; //points to the output of the capture
static camera_config_t camera_config = {
.pin_pwdn = PWDN_GPIO_NUM,
.pin_reset = RESET_GPIO_NUM,
.pin_xclk = XCLK_GPIO_NUM,
.pin_sscb_sda = SIOD_GPIO_NUM,
.pin_sscb_scl = SIOC_GPIO_NUM,
.pin_d7 = Y9_GPIO_NUM,
.pin_d6 = Y8_GPIO_NUM,
.pin_d5 = Y7_GPIO_NUM,
.pin_d4 = Y6_GPIO_NUM,
.pin_d3 = Y5_GPIO_NUM,
.pin_d2 = Y4_GPIO_NUM,
.pin_d1 = Y3_GPIO_NUM,
.pin_d0 = Y2_GPIO_NUM,
.pin_vsync = VSYNC_GPIO_NUM,
.pin_href = HREF_GPIO_NUM,
.pin_pclk = PCLK_GPIO_NUM,
//XCLK 20MHz or 10MHz for OV2640 double FPS (Experimental)
.xclk_freq_hz = 20000000,
.ledc_timer = LEDC_TIMER_0,
.ledc_channel = LEDC_CHANNEL_0,
.pixel_format = PIXFORMAT_JPEG, //YUV422,GRAYSCALE,RGB565,JPEG
.frame_size = FRAMESIZE_QVGA, //QQVGA-UXGA Do not use sizes above QVGA when not JPEG
.jpeg_quality = 12, //0-63 lower number means higher quality
.fb_count = 1, //if more than one, i2s runs in continuous mode. Use only with JPEG
.fb_location = CAMERA_FB_IN_PSRAM,
.grab_mode = CAMERA_GRAB_WHEN_EMPTY,
};
/* Function definitions ------------------------------------------------------- */
bool ei_camera_init(void);
void ei_camera_deinit(void);
bool ei_camera_capture(uint32_t img_width, uint32_t img_height, uint8_t *out_buf) ;
/**
* @brief Arduino setup function
*/
void setup()
{
// put your setup code here, to run once:
Serial.begin(115200);
//comment out the below line to start inference immediately after upload
while (!Serial);
Serial.println("Edge Impulse Inferencing Demo");
if (ei_camera_init() == false) {
ei_printf("Failed to initialize Camera!\r\n");
}
else {
ei_printf("Camera initialized\r\n");
}
ei_printf("\nStarting continious inference in 2 seconds...\n");
ei_sleep(2000);
}
/**
* @brief Get data and run inferencing
*
* @param[in] debug Get debug info if true
*/
void loop()
{
// instead of wait_ms, we'll wait on the signal, this allows threads to cancel us...
if (ei_sleep(5) != EI_IMPULSE_OK) {
return;
}
snapshot_buf = (uint8_t*)malloc(EI_CAMERA_RAW_FRAME_BUFFER_COLS * EI_CAMERA_RAW_FRAME_BUFFER_ROWS * EI_CAMERA_FRAME_BYTE_SIZE);
// check if allocation was successful
if(snapshot_buf == nullptr) {
ei_printf("ERR: Failed to allocate snapshot buffer!\n");
return;
}
ei::signal_t signal;
signal.total_length = EI_CLASSIFIER_INPUT_WIDTH * EI_CLASSIFIER_INPUT_HEIGHT;
signal.get_data = &ei_camera_get_data;
if (ei_camera_capture((size_t)EI_CLASSIFIER_INPUT_WIDTH, (size_t)EI_CLASSIFIER_INPUT_HEIGHT, snapshot_buf) == false) {
ei_printf("Failed to capture image\r\n");
free(snapshot_buf);
return;
}
// Run the classifier
ei_impulse_result_t result = { 0 };
EI_IMPULSE_ERROR err = run_classifier(&signal, &result, debug_nn);
if (err != EI_IMPULSE_OK) {
ei_printf("ERR: Failed to run classifier (%d)\n", err);
return;
}
// print the predictions
ei_printf("Predictions (DSP: %d ms., Classification: %d ms., Anomaly: %d ms.): \n",
result.timing.dsp, result.timing.classification, result.timing.anomaly);
#if EI_CLASSIFIER_OBJECT_DETECTION == 1
ei_printf("Object detection bounding boxes:\r\n");
for (uint32_t i = 0; i < result.bounding_boxes_count; i++) {
ei_impulse_result_bounding_box_t bb = result.bounding_boxes[i];
if (bb.value == 0) {
continue;
}
ei_printf(" %s (%f) [ x: %u, y: %u, width: %u, height: %u ]\r\n",
bb.label,
bb.value,
bb.x,
bb.y,
bb.width,
bb.height);
}
// Print the prediction results (classification)
#else
ei_printf("Predictions:\r\n");
for (uint16_t i = 0; i < EI_CLASSIFIER_LABEL_COUNT; i++) {
ei_printf(" %s: ", ei_classifier_inferencing_categories[i]);
ei_printf("%.5f\r\n", result.classification[i].value);
}
#endif
// Print anomaly result (if it exists)
#if EI_CLASSIFIER_HAS_ANOMALY
ei_printf("Anomaly prediction: %.3f\r\n", result.anomaly);
#endif
#if EI_CLASSIFIER_HAS_VISUAL_ANOMALY
ei_printf("Visual anomalies:\r\n");
for (uint32_t i = 0; i < result.visual_ad_count; i++) {
ei_impulse_result_bounding_box_t bb = result.visual_ad_grid_cells[i];
if (bb.value == 0) {
continue;
}
ei_printf(" %s (%f) [ x: %u, y: %u, width: %u, height: %u ]\r\n",
bb.label,
bb.value,
bb.x,
bb.y,
bb.width,
bb.height);
}
#endif
free(snapshot_buf);
}
/**
* @brief Setup image sensor & start streaming
*
* @retval false if initialisation failed
*/
bool ei_camera_init(void) {
if (is_initialised) return true;
#if defined(CAMERA_MODEL_ESP_EYE)
pinMode(13, INPUT_PULLUP);
pinMode(14, INPUT_PULLUP);
#endif
//initialize the camera
esp_err_t err = esp_camera_init(&camera_config);
if (err != ESP_OK) {
Serial.printf("Camera init failed with error 0x%x\n", err);
return false;
}
sensor_t * s = esp_camera_sensor_get();
// initial sensors are flipped vertically and colors are a bit saturated
if (s->id.PID == OV3660_PID) {
s->set_vflip(s, 1); // flip it back
s->set_brightness(s, 1); // up the brightness just a bit
s->set_saturation(s, 0); // lower the saturation
}
#if defined(CAMERA_MODEL_M5STACK_WIDE)
s->set_vflip(s, 1);
s->set_hmirror(s, 1);
#elif defined(CAMERA_MODEL_ESP_EYE)
s->set_vflip(s, 1);
s->set_hmirror(s, 1);
s->set_awb_gain(s, 1);
#endif
is_initialised = true;
return true;
}
/**
* @brief Stop streaming of sensor data
*/
void ei_camera_deinit(void) {
//deinitialize the camera
esp_err_t err = esp_camera_deinit();
if (err != ESP_OK)
{
ei_printf("Camera deinit failed\n");
return;
}
is_initialised = false;
return;
}
/**
* @brief Capture, rescale and crop image
*
* @param[in] img_width width of output image
* @param[in] img_height height of output image
* @param[in] out_buf pointer to store output image, NULL may be used
* if ei_camera_frame_buffer is to be used for capture and resize/cropping.
*
* @retval false if not initialised, image captured, rescaled or cropped failed
*
*/
bool ei_camera_capture(uint32_t img_width, uint32_t img_height, uint8_t *out_buf) {
bool do_resize = false;
if (!is_initialised) {
ei_printf("ERR: Camera is not initialized\r\n");
return false;
}
camera_fb_t *fb = esp_camera_fb_get();
if (!fb) {
ei_printf("Camera capture failed\n");
return false;
}
bool converted = fmt2rgb888(fb->buf, fb->len, PIXFORMAT_JPEG, snapshot_buf);
esp_camera_fb_return(fb);
if(!converted){
ei_printf("Conversion failed\n");
return false;
}
if ((img_width != EI_CAMERA_RAW_FRAME_BUFFER_COLS)
|| (img_height != EI_CAMERA_RAW_FRAME_BUFFER_ROWS)) {
do_resize = true;
}
if (do_resize) {
ei::image::processing::crop_and_interpolate_rgb888(
out_buf,
EI_CAMERA_RAW_FRAME_BUFFER_COLS,
EI_CAMERA_RAW_FRAME_BUFFER_ROWS,
out_buf,
img_width,
img_height);
}
return true;
}
static int ei_camera_get_data(size_t offset, size_t length, float *out_ptr)
{
// we already have a RGB888 buffer, so recalculate offset into pixel index
size_t pixel_ix = offset * 3;
size_t pixels_left = length;
size_t out_ptr_ix = 0;
while (pixels_left != 0) {
// Swap BGR to RGB here
// due to https://github.com/espressif/esp32-camera/issues/379
out_ptr[out_ptr_ix] = (snapshot_buf[pixel_ix + 2] << 16) + (snapshot_buf[pixel_ix + 1] << 8) + snapshot_buf[pixel_ix];
// go to the next pixel
out_ptr_ix++;
pixel_ix+=3;
pixels_left--;
}
// and done!
return 0;
}
#if !defined(EI_CLASSIFIER_SENSOR) || EI_CLASSIFIER_SENSOR != EI_CLASSIFIER_SENSOR_CAMERA
#error "Invalid model for current sensor"
#endif
However, when I attempt to compile the code, I receive the following error:
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\conv.cpp: In function 'TfLiteStatus tflite::{anonymous}::Prepare(TfLiteContext*, TfLiteNode*)':
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\conv.cpp:1789:67: error: either all initializer clauses should be designated or none of them should be
1789 | .channels = input->dims->data[3], 1
| ^
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\conv.cpp:1793:68: error: either all initializer clauses should be designated or none of them should be
1793 | .channels = output->dims->data[3], 1
| ^
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\conv.cpp:1795:80: error: either all initializer clauses should be designated or none of them should be
1795 | data_dims_t filter_dims = {.width = filter_width, .height = filter_height, 0, 0};
| ^
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\conv.cpp: In function 'void tflite::{anonymous}::EvalQuantizedPerChannel(TfLiteContext*, TfLiteNode*, const TfLiteConvParams&, const NodeData&, const TfLiteEvalTensor*, const TfLiteEvalTensor*, const TfLiteEvalTensor*, TfLiteEvalTensor*)':
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\conv.cpp:1883:58: error: either all initializer clauses should be designated or none of them should be
1883 | .channels = input_depth, 1
| ^
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\conv.cpp:1887:59: error: either all initializer clauses should be designated or none of them should be
1887 | .channels = output_depth, 1
| ^
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\conv.cpp:1889:80: error: either all initializer clauses should be designated or none of them should be
1889 | data_dims_t filter_dims = {.width = filter_width, .height = filter_height, 0, 0};
| ^
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\depthwise_conv.cpp: In function 'void tflite::{anonymous}::EvalQuantizedPerChannel(TfLiteContext*, TfLiteNode*, const TfLiteDepthwiseConvParams&, const NodeData&, const TfLiteEvalTensor*, const TfLiteEvalTensor*, const TfLiteEvalTensor*, TfLiteEvalTensor*)':
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\depthwise_conv.cpp:1727:58: error: either all initializer clauses should be designated or none of them should be
1727 | .channels = input_depth, 1
| ^
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\depthwise_conv.cpp:1731:59: error: either all initializer clauses should be designated or none of them should be
1731 | .channels = output_depth, 1
| ^
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\depthwise_conv.cpp:1733:80: error: either all initializer clauses should be designated or none of them should be
1733 | data_dims_t filter_dims = {.width = filter_width, .height = filter_height, 0, 0};
| ^
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\depthwise_conv.cpp: In function 'TfLiteStatus tflite::{anonymous}::Prepare(TfLiteContext*, TfLiteNode*)':
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\depthwise_conv.cpp:1836:67: error: either all initializer clauses should be designated or none of them should be
1836 | .channels = input->dims->data[3], 1
| ^
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\depthwise_conv.cpp:1840:68: error: either all initializer clauses should be designated or none of them should be
1840 | .channels = output->dims->data[3], 1
| ^
C:\Users\Somebody\Documents\Arduino\libraries\Bill_detector_inferencing\src\edge-impulse-sdk\tensorflow\lite\micro\kernels\depthwise_conv.cpp:1842:80: error: either all initializer clauses should be designated or none of them should be
1842 | data_dims_t filter_dims = {.width = filter_width, .height = filter_height, 0, 0};
| ^
exit status 1
Compilation error: exit status 1
In an attempt to fix this problem, I tried deleting the "1"s which were not "designated" from the library files. This allowed the code to compile, but when the code was uploaded to the ESP32, random letters, numbers and symbols were sent back to the serial monitor non-stop. The same result occurred when I attempted a solution from the Edge Impulse Forum which said, "Just editing the file ei_classifier_config.h in exported Arduino library folder: /scr/edge-impulse-sdk/classifier/:
Disabling #define EI_CLASSIFIER_TFLITE_ENABLE_ESP_NN 1 and set it to 0 will allow the project to compile ."
This also allowed the code to compile, put it resulted in the same outcome of the serial monitor being sent random numbers and symbols non-stop from the ESP32-CAM, such as �x�xxx�x�x��x�x�x��x�xxxx�x��xx�x�x�xxx�x�x��x�x�x.
Any advice on how to solve these issues would be greatly appreciated, thanks.