Thanks so much @louis, that code is fairly understandable, should be a good base, along with the two versions from Edge Impulse above.
void image_resize_linear(uint8_t *dst_image, uint8_t *src_image, int dst_w, int dst_h, int dst_c, int src_w, int src_h)
Just checking is int dst_c the number of channels meaning RGB is 3 and GRAYSCALE is 1?
Somehow I logged in differently this is still @rocksetta.
This seems very wrong. @louis, I am struggling with how to get the out_ptr into the features_signal structure. This is what I have tried so far, seems very wasteful of memory. It does compile but flashes red on loading to the Portenta.
int myCamResult = myCam.grab(sdram_frame_buffer); // myCamResult should be zero
// the features are stored into flash, and we don't want to load everything into RAM
signal_t features_signal;
features_signal.total_length = CUTOUT_COLS * CUTOUT_ROWS;
float model_input_buffer[features_signal.total_length];
//features_signal.get_data = &cutout_get_data; // this activated the old code
// somehow activate resize???
// void image_resize_linear(uint8_t *dst_image, uint8_t *src_image, int dst_w, int dst_h, int dst_c, int src_w, int src_h)
uint8_t * tmp_buffer = (uint8_t *) malloc(features_signal.total_length);
image_resize_linear( tmp_buffer, sdram_frame_buffer, 96,96, 1 /* 1 = GRAYSCALE */, 320,320 );
// convert int_8 to float
for (int i=0; i < features_signal.total_length; i++){
model_input_buffer[i] = tmp_buffer[i] / 255.0f;
}
features_signal.get_data((unsigned int)sizeof(uint8_t), (unsigned int)features_signal.total_length, model_input_buffer);
free(tmp_buffer);
Hello @Rocksetta,
I just checked how I did the project using the ESP32 Cam to see if there was any differences, in fact, the way I did allocated the pointer using Espressif SDK was using this function dl_matrix3du_alloc âŚ
This will be different with the Portenta.
Also, to answer you on this parameter: int dst_c it is the channel (so 3 for RGB). In your case, I see that you are using grayscale and from what I see in the header file (https://github.com/espressif/esp-dl/blob/420fc7e219ba98e40a5493b9d4be270db2f2d724/image_util/include/image_util.h)
/**
* @brief Resize the image in RGB888 format via bilinear interpolation
*
* @param dst_image The output image
* @param src_image Source image
* @param dst_w Width of the output image
* @param dst_h Height of the output image
* @param dst_c Channel of the output image
* @param src_w Width of the source image
* @param src_h Height of the source image
*/
void image_resize_linear(uint8_t *dst_image, uint8_t *src_image, int dst_w, int dst_h, int dst_c, int src_w, int src_h);
It has to be in RGB888 format to use this function⌠I might have misread your initial question.
If needed, here is an arduino sketch I wrote to show how it works with the ESP32 Cam + Edge Impulse
Regards,
Louis
If you want to only resize (and not crop) from 320x320 to 96x96 you can try this (on the Portenta H7):
Iâve used magic numbers just for verbosity.
cam.grab(ei_camera_frame_buffer);
resizeImage(320, 320, // <-- input buf resolution
ei_camera_frame_buffer, // <-- input buf
96, 96, // output buf resolutions
ei_camera_frame_buffer, // <-- output buf can be the same
8); // <-- bits per pixel
ei::signal_t signal;
signal.total_length = 96 * 96; // <-- in pixels
signal.get_data = &ei_camera_cutout_get_data;
static inline void mono_to_rgb(uint8_t mono_data, uint8_t *r, uint8_t *g, uint8_t *b) {
uint8_t v = mono_data;
*r = *g = *b = v;
}
int ei_camera_cutout_get_data(size_t offset, size_t length, float *out_ptr) {
size_t bytes_left = length;
size_t out_ptr_ix = 0;
// read byte for byte
while (bytes_left != 0) {
// grab the value and convert to r/g/b
uint8_t pixel = ei_camera_frame_buffer[offset];
uint8_t r, g, b;
mono_to_rgb(pixel, &r, &g, &b);
// then convert to out_ptr format
float pixel_f = (r << 16) + (g << 8) + b;
out_ptr[out_ptr_ix] = pixel_f;
// and go to the next pixel
out_ptr_ix++;
offset++;
bytes_left--;
}
// and done!
return 0;
}
Your amazing @rjames, 
thanks so much for the code examples. This is the first time I have ever had the Arduino Portenta using all 320x320 camera pixels resized to a 96x96 Edge Impulse model, using the SDRAM of the Portenta for the camera buffer.
Look how fast this little beast is processing.
My version of Raulâs code is here .
Thatâs awesome news! 
// Raul
Raul @rjames, any hints about testing multi-object âbounding boxes object detectionâ instead of what we have working for single object âone label per dataâ ?
I know from my work with WASM that the differences between the two types of code are very small. I am wondering if this line still grabs the result correctly
EI_IMPULSE_ERROR res = run_classifier(&signal, &result, false /* debug */);
Also
the result structure has changed for multi-object, but I canât find any information about the new structure other than the header file ei_classifier_types.h. I think from my WASM the calls look something like this.
result.results.length
result.results[i].value
result.results[i].label
result.results[i].x, result.results[i].y, result.results[i].width, result.results[i].height
result.anomaly
but from the header file it is probably more like:
result.bounding_boxes[i].x
result.bounding_boxes[i].y
result.bounding_boxes[i].width
result.bounding_boxes[i].height
result.bounding_boxes[i].value
result.bounding_boxes[i].label
result.timing.sampling
result.timing.dsp
result.timing.classification
result.timing.anomaly
result.anomaly
Any confirmation here. Not expecting bounding boxes to work well, just wondering if it works at all on the Portenta. It was very slow on the web browser.