Search found 90 matches

by chrisPyres66
Thu Jun 13, 2019 10:42 am
Forum: Technical Discussion
Topic: upper quartile
Replies: 1
Views: 104

upper quartile

Dear all, I try to analyse area of image, and i get different values of upper quartile for the same area. Here is the test code : import sensor, image, time sensor.reset() sensor.set_pixformat(sensor.GRAYSCALE) sensor.set_framesize(sensor.QVGA) sensor.skip_frames(time=1000) while(True): img = sensor...
by chrisPyres66
Thu Jun 06, 2019 12:12 pm
Forum: Technical Discussion
Topic: image areas analyse
Replies: 1
Views: 187

image areas analyse

Dear all, I try to analysesome areas of the image but i am not sure if i do it well because my results are not what i expected. For exemple, i created a bmp image, as i did it for masking, with the background at value 0x00 and an area in the middle with 0xFF value. I tried to do an AND boolean opera...
by chrisPyres66
Thu Jun 06, 2019 11:45 am
Forum: Technical Discussion
Topic: Precision of RGB Gain
Replies: 4
Views: 350

Re: Precision of RGB Gain

Thanks, I tried to modify the gain register at address 0x00 and read the db gain with sensor.get_gain_db(). Here is the code, and it is not linear between register and the db gain. import sensor, image, time sensor.reset() sensor.set_pixformat(sensor.GRAYSCALE) sensor.set_framesize(sensor.VGA) senso...
by chrisPyres66
Tue Jun 04, 2019 10:53 am
Forum: Technical Discussion
Topic: set gain ceiling
Replies: 4
Views: 171

Re: set gain ceiling

well, i see
- set_gainceiling : 2, 4, 8, 16 or 32 for x2, x4, x8, x16 or x32
- set_auto_gain : 2 to 32db

But i dont still understand teh relationship between gain and register ?
Thanks,
by chrisPyres66
Tue Jun 04, 2019 9:18 am
Forum: Technical Discussion
Topic: Precision of RGB Gain
Replies: 4
Views: 350

Precision of RGB Gain

Dear all, I try to understand how works the gain in OV7725 camera and i am lost without speaking about analog gain. Firstly, there is the main gain at register address 0x00 which can be used with these both python functions where the gain is in db : - sensor.set_auto_gain( False, gain_db=(1 to 32db)...
by chrisPyres66
Tue Jun 04, 2019 8:08 am
Forum: Technical Discussion
Topic: set gain ceiling
Replies: 4
Views: 171

set gain ceiling

Dear all, I try to understand how works the gain in the OV7725 camera, and i stopped on the gain ceiling. To set the gain ceiling there is 2 ways in python : - sensor.set_gainceiling(4) - sensor.set_auto_gain(True, gain_db_ceiling=4) which both write at the COM9 register but the c language codes do ...
by chrisPyres66
Tue Jun 04, 2019 2:42 am
Forum: General Topics
Topic: Do i have to skipframe if i change format or frame size without ressetting ?
Replies: 3
Views: 187

Re: Do i have to skipframe if i change format or frame size without ressetting ?

Thanks, i effectively met this case.

How can i be sure of the lmean level before taking the first snapshot in RGB565 and VGA configuration ?
by chrisPyres66
Mon Jun 03, 2019 5:48 am
Forum: General Topics
Topic: Do i have to skipframe if i change format or frame size without ressetting ?
Replies: 3
Views: 187

Do i have to skipframe if i change format or frame size without ressetting ?

Dear all, I have different light conditions and i want to test the lmean before taking the first snapshot. Unfortunately, i cant do sensor.snapshot().histogram().get_statistics() in RGB565 and VGA configuration. Therefore i do it in smaller configuration i change after like this : import sensor, ima...
by chrisPyres66
Mon May 13, 2019 5:04 am
Forum: Technical Discussion
Topic: LBP
Replies: 10
Views: 2443

Re: LBP

well, the uniform matrix is to reduce the number of lbp (256 possibility) to 59 most common.
So it is not usefull to change for specific use.
Thanks,
by chrisPyres66
Fri May 10, 2019 6:16 am
Forum: Technical Discussion
Topic: LBP
Replies: 10
Views: 2443

Re: LBP

Well i understand than lbp_weights has a high value around eyes, medium value for mouth and ear, then low level for cheeks.
If i want to have a neutral use, i can set 1 for all the 7x7 matrix.

I dont understand what is for the uniform_tbl matrix ?
by chrisPyres66
Thu May 09, 2019 10:44 am
Forum: Technical Discussion
Topic: LBP
Replies: 10
Views: 2443

Re: LBP

Thanks,
I red lbp.c and i discovered the weight are optimized for face recognition.
I would like to use for another use, what is the default values, and how can i define it to my own case ?
by chrisPyres66
Thu May 09, 2019 9:01 am
Forum: Technical Discussion
Topic: LBP
Replies: 10
Views: 2443

Re: LBP

Wowwwww, i tested a 6x6 lbp on M7, and it works fine.
Which file from github i have to update to get this ?
Thanks,
by chrisPyres66
Tue May 07, 2019 8:27 am
Forum: Technical Discussion
Topic: LBP
Replies: 10
Views: 2443

Re: LBP

Below is the simplified code, where you can define the number of line and column which define the number of areas where the lbp is defined and checked. I tested the M7 and H7 camera, and both get problem if i increase the number of line and column. With openmv 2.2.0 : For M7 (rev 3.4.1), in VGA : - ...
by chrisPyres66
Mon May 06, 2019 10:49 am
Forum: Technical Discussion
Topic: LBP
Replies: 10
Views: 2443

LBP

Dear All, I use lbp descriptor to recognize a pattern and, to filter local noise, i divide the image in several part with each a lbp descriptor. My problem is if i use more than 4 lbp pattern, whatever the resolution, i have frequently deconnexion and it does not seem stable. Do you have any knowled...
by chrisPyres66
Thu Apr 04, 2019 6:11 am
Forum: General Topics
Topic: Nvidia digits to train cnn with caffe
Replies: 3
Views: 6166

Re: Nvidia digits to train cnn with caffe

Nice, do you have some advice because i dont manage to quantize to openmv camera with : python2 ~/openmv/ml/cmsisnn/nn_quantizer.py --gpu --model ./quantizer.prototxt --weights ./snapshot_iter_240.caffemodel --save ./V22_Lenet.pkl I used a lenet network with my own image set. As nvidia digits is use...
by chrisPyres66
Wed Apr 03, 2019 4:47 am
Forum: General Topics
Topic: Nvidia digits to train cnn with caffe
Replies: 3
Views: 6166

Nvidia digits to train cnn with caffe

Dear all,

Do you know if it is possible to use Nvidia digits software to train CNN and then convert it to openmv ?

Thanks,
by chrisPyres66
Mon Mar 18, 2019 10:04 am
Forum: General Topics
Topic: M7 camera memory solutions
Replies: 1
Views: 2642

M7 camera memory solutions

Dear all, As everybody waiting the new H7 camera, I have M7 camera memory problem with cnn and heap size or heap variable allocation along time. If I would like to improve this, i am not sure to well understand how it works. Flash is divided like this - Bootloader : 32 Ko - Embedded Flash Drive : 96...
by chrisPyres66
Mon Mar 11, 2019 4:47 am
Forum: General Topics
Topic: white and cold image colors for M7 (OV7725) => blur image
Replies: 6
Views: 3118

Re: white and cold image colors for M7 (OV7725) => blur image

Ok i tested this and it seems ok sensor.__write_reg(0x24, 0x40) # New: 0x40 \ default: 0x75 / OPENMV: 0x58 sensor.__write_reg(0x25, 0x30) # New: 0x30 \ default: 0x63 / OPENMV: 0x48 sensor.__write_reg(0x26, 0xa1) # New: 0xa1 \ default: 0xD4 / OPENMV: 0xC3 sensor.__write_reg(0x0d, 0x71) # New: 0x71 \ ...
by chrisPyres66
Fri Mar 08, 2019 6:01 am
Forum: General Topics
Topic: white and cold image colors for M7 (OV7725) => blur image
Replies: 6
Views: 3118

Re: white and cold image colors for M7 (OV7725) => blur image

Dear, In place of turning auto gain and auto white balance off after 200ms, i changed the camera registers AEW and AEB in helloworld.py like this : import sensor, image, time sensor.reset() sensor.set_pixformat(sensor.RGB565) sensor.set_framesize(sensor.VGA) sensor.__write_reg(0x24, 0x40) #New: 0x40...
by chrisPyres66
Wed Feb 27, 2019 6:23 am
Forum: General Topics
Topic: white and cold image colors for M7 (OV7725) => blur image
Replies: 6
Views: 3118

white and cold image colors for M7 (OV7725) => blur image

Dear all, I have got another camera with OV7725 and the image colors are more hot and more red compare to the M7 which the colors are more white and cold. This whiteness seems to blur the images like big aperture reduce depth of field. This other camera uses the OV529 ftom omnivision too, i dont kno...
by chrisPyres66
Thu Feb 14, 2019 4:47 am
Forum: General Topics
Topic: exposure and gain control
Replies: 11
Views: 3094

Re: exposure and gain control

lol, ok you mean the last current firmware.

I am not sure which function does this gamma correction.
Is it the function for histogram ?

Thanks,
by chrisPyres66
Wed Feb 13, 2019 7:57 am
Forum: General Topics
Topic: exposure and gain control
Replies: 11
Views: 3094

Re: exposure and gain control

Hi, the camera doesn't support gain/exposure for a small part of the image. As for the min and maxes, the gain has a max of 32 or so. The exposure isn't really limited by anything. But, if you set it very high the FPS will go to near 0. The exposure is based on the pixel readout line times which we...
by chrisPyres66
Tue Feb 12, 2019 11:39 am
Forum: General Topics
Topic: exposure and gain control
Replies: 11
Views: 3094

exposure and gain control

Dear all, As i use a small part of the image, i try to control the exposure and gain to have the highest contrast with different ambiant lights. Is there a possibility to have the automatic gain and exposure control on a small part of the image ? sensor.set_windowing((128,128)) only cut the image (w...
by chrisPyres66
Mon Jan 28, 2019 10:56 am
Forum: General Topics
Topic: Draw Net, learning curve and intermediate images of CNN training
Replies: 4
Views: 2308

Re: Draw Net, learning curve and intermediate images of CNN training

To complete this post, i just discoverted than caffe have curve plotting python program. Here is the way i use it : 1- Create log file cd ~/openmv/ml/cmsisnn/ ./models/lettre_O_V3/fnt-train.sh >> ./models/lettre_O_V3/fnt-lettre_O_V3-output.log 2>&1 2- Draw plot Supported chart types: 0: Test_accurac...
by chrisPyres66
Mon Jan 28, 2019 2:42 am
Forum: General Topics
Topic: Draw Net, learning curve and intermediate images of CNN training
Replies: 4
Views: 2308

Re: Draw Net, learning curve and intermediate images of CNN training

yes you are right i jump to caffe forum
thanks,
by chrisPyres66
Fri Jan 25, 2019 5:48 am
Forum: General Topics
Topic: Draw Net, learning curve and intermediate images of CNN training
Replies: 4
Views: 2308

Draw Net, learning curve and intermediate images of CNN training

Dear all, I try and understand how CNN training works by having the net image, learning curve and intermediate images of CNN training. For draw the net i use ~/caffe/python/draw_net.py ~/openmv/ml/cmsisnn/models/lettre_O_V3/fnt-lettre_O_V3_train_test.prototxt ~/openmv/ml/cmsisnn/models/fnt-lettre_O_...
by chrisPyres66
Fri Jan 25, 2019 2:56 am
Forum: General Topics
Topic: advices to train cnn
Replies: 7
Views: 3151

Re: advices to train cnn

Yes i scored 100% after train, test and quantize.
net.forward works well with an image with same size, ratio object/image size and binary characters.
I dont know how to get working the network with net.search at the moment...
Thanks,
by chrisPyres66
Thu Jan 24, 2019 11:04 am
Forum: General Topics
Topic: advices to train cnn
Replies: 7
Views: 3151

Re: advices to train cnn

Yes you are right, the explanations are very good and clear. To reduce the size of the network file, a simple way is to reduce the num_output in convolution layers of the train_test.prototxt architecture file. As you said, the cnn learn only as much as the datas have. My feeling is if you have a lot...
by chrisPyres66
Thu Jan 24, 2019 3:03 am
Forum: Technical Discussion
Topic: Quantize network stops at "Network initialization done." step
Replies: 1
Views: 353

Quantize network stops at "Network initialization done." step

Hello, I trained and i try to quantize the network but it stops at "Network initialization done." step. The commands is : python2 nn_quantizer.py --gpu --model models/lettre_O_V1/lettre_O_train_test.prototxt --weights models/lettre_O_V1/lettre_O_iter_1300.caffemodel --save models/lettre_O_V1/lettre_...
by chrisPyres66
Tue Jan 22, 2019 8:42 am
Forum: General Topics
Topic: advices to train cnn
Replies: 7
Views: 3151

Re: advices to train cnn

well thanks, As you said, i suppressed directory but i still have a file.network around 90K what ever the number of letter and it is too big for the M7 ??? I try to train with different other parameters of solver.prototext to minimize the size without success at the moment. Any help would be appreci...
by chrisPyres66
Mon Jan 21, 2019 11:47 am
Forum: General Topics
Topic: advices to train cnn
Replies: 7
Views: 3151

advices to train cnn

Hello all, I try to train a cnn with caffe to detect the letter "OK" or not. My first CNN is not very good and i would like to have your advices. I got fonts in png (white font on black background with 28x28px) for the letter O and K (real size is more around 120x120px, and the letter are more black...
by chrisPyres66
Fri Jan 18, 2019 5:18 am
Forum: General Topics
Topic: Pb to quantize the network
Replies: 4
Views: 4016

Re: Pb to quantize the network

Dear, I followed your log but my caffe was not in the same directory. Then i change path in train.sh and test.sh to get them working. My problem was simply because : - i did not compile caffe until the end (test, runtest and distribute) - i did not export pythonpath in the bashrc - i tried to use py...
by chrisPyres66
Thu Jan 17, 2019 9:51 am
Forum: Technical Discussion
Topic: compress ==> OSError: Out of memory !
Replies: 10
Views: 2054

Re: compress ==> OSError: Out of memory !

Hello, Sorry for late answer, i was lost in stm32F7 low power mode. I downloaded the last 2.1.0 openmv ide and the camera version is 3.3.0. Here is the code where i included your solution/question : import sensor, image, pyb, time, gc red_led=pyb.LED(1) green_led=pyb.LED(2) blue_led=pyb.LED(3) senso...
by chrisPyres66
Tue Jan 15, 2019 11:53 am
Forum: General Topics
Topic: Pb to quantize the network
Replies: 4
Views: 4016

Pb to quantize the network

hello, I have a new computer with - ubuntu 18.04 - carte nvidia geforce gtx 1080ti with gpu (driver 410.79) - cuda 10.0.130 - python 3.6.7 - caffe and i try to follow your link : https://github.com/openmv/openmv/tree/master/ml/cmsisnn to train a cifar 10 model I am stopped at the step : python3 /hom...
by chrisPyres66
Wed Dec 19, 2018 3:55 am
Forum: Technical Discussion
Topic: compress ==> OSError: Out of memory !
Replies: 10
Views: 2054

Re: compress ==> OSError: Out of memory !

You are right the connexion is not lost but it is not possible to disconnect without unplugging the usb cable.
It is like the camera is too busy to answer.

Limited the quality at 90 maximum will solve the problem...
by chrisPyres66
Wed Dec 19, 2018 3:47 am
Forum: Technical Discussion
Topic: problem when i receive data on Uart rx when i read
Replies: 12
Views: 2626

Re: problem when i receive data on Uart rx when i read

I am lost in github but the modification works for UART ! Here are the results to get the last modifications : - git pull in in src/micropython gives Your are not in a branch... - git remote -v in openmv/ gives : origin https://github.cm/openmv/openmv.git (fetch) origin https://github.cm/openmv/open...
by chrisPyres66
Tue Dec 18, 2018 4:29 am
Forum: Technical Discussion
Topic: problem when i receive data on Uart rx when i read
Replies: 12
Views: 2626

Re: problem when i receive data on Uart rx when i read

Opposite to your firmware, the last git have the same previous behavior.
by chrisPyres66
Tue Dec 18, 2018 4:26 am
Forum: Technical Discussion
Topic: compress ==> OSError: Out of memory !
Replies: 10
Views: 2054

Re: compress ==> OSError: Out of memory !

Hello, I tested the last git version (3.3.0 displayed on openmv ide) with : import sensor, image, pyb, time, gc red_led=pyb.LED(1) blue_led=pyb.LED(3) red_led.off() blue_led.off() sensor.reset() sensor.set_pixformat(sensor.RGB565) sensor.set_framesize(sensor.VGA) sensor.skip_frames(time=500) quality...
by chrisPyres66
Mon Dec 17, 2018 5:14 am
Forum: Technical Discussion
Topic: problem when i receive data on Uart rx when i read
Replies: 12
Views: 2626

Re: problem when i receive data on Uart rx when i read

Tx it works with my code test, do you github it ?
I could test this and jpg exception.
by chrisPyres66
Fri Dec 14, 2018 3:08 am
Forum: Technical Discussion
Topic: problem when i receive data on Uart rx when i read
Replies: 12
Views: 2626

Re: problem when i receive data on Uart rx when i read

Lol, ok i try again ! Here is a new test code with image snapshot : import pyb,time, sensor sensor.reset() sensor.set_pixformat(sensor.RGB565) sensor.set_framesize(sensor.QVGA) sensor.skip_frames(time = 2000) clock = time.clock() uart=pyb.UART(3,14400) uart.init(14400, bits=8, parity=None, stop=1) w...
by chrisPyres66
Thu Dec 13, 2018 2:55 am
Forum: Technical Discussion
Topic: problem when i receive data on Uart rx when i read
Replies: 12
Views: 2626

Re: problem when i receive data on Uart rx when i read

Well, i discovered the problem when i tried to send image over UART to a master which does something else, lose a part of the data and try to restart a new synchronization. To reproduce the behavior, I send several datas by frame (like 0x0F 0x00 0x0F 0x00 0x0F 0x00 0x0F 0x00) every ~0.5s when the ca...
by chrisPyres66
Wed Dec 12, 2018 6:50 am
Forum: Technical Discussion
Topic: problem when i receive data on Uart rx when i read
Replies: 12
Views: 2626

problem when i receive data on Uart rx when i read

Hello, I have got a problem when i receive data on Uart rx when i read. Here is my test code : import pyb,time red_led = pyb.LED(1) red_led.off() uart=pyb.UART(3,14400) uart.init(14400, bits=8, parity=None, stop=1) #, timeout_char=20 while(True): time.sleep(500) if uart.any(): uchar=uart.read(1) pri...
by chrisPyres66
Tue Dec 11, 2018 3:14 am
Forum: Technical Discussion
Topic: compress ==> OSError: Out of memory !
Replies: 10
Views: 2054

Re: compress ==> OSError: Out of memory !

Thanks for your reply. I tested your solution below : import sensor, image, pyb red_led=pyb.LED(1) blue_led=pyb.LED(3) red_led.off() blue_led.off() sensor.reset() sensor.set_pixformat(sensor.RGB565) sensor.set_framesize(sensor.VGA) sensor.skip_frames(time=500) quality = 94 while(True): img=sensor.sn...
by chrisPyres66
Mon Dec 10, 2018 8:19 am
Forum: Technical Discussion
Topic: compress ==> OSError: Out of memory !
Replies: 10
Views: 2054

compress ==> OSError: Out of memory !

Hello, I try to compress image continuously (every 10s) and i have some problem with the level of compression (between 0 and 100) Here is a test code : import sensor, image, pyb red_led=pyb.LED(1) red_led.off() sensor.reset() sensor.set_pixformat(sensor.RGB565) sensor.set_framesize(sensor.VGA) senso...
by chrisPyres66
Wed Dec 05, 2018 9:48 am
Forum: Project Discussion
Topic: flashing led detection with changing ambiant light
Replies: 1
Views: 3452

flashing led detection with changing ambiant light

Dear all, I would like to discuss the best way (accuracy and consumption) to detect a flashing green led with a changing ambiant light from night to day. The led is lighting very quickly (around 20ms) every 4s. To be accurate, i used QQQVGA frame rate to have 84fps and catch the flashing light. I tr...
by chrisPyres66
Wed Dec 05, 2018 3:02 am
Forum: Technical Discussion
Topic: low power waiting for uart rx
Replies: 4
Views: 1401

Re: low power waiting for uart rx

Here is the simplified code which works without activating the sleep mode import pyb, machine red_led = pyb.LED(1) red_led.off() uart = pyb.UART(3,14400) uart.init(14400, bits=8, parity=None, stop=1, timeout_char=20) while(True): #machine.sleep() uchar=uart.read(1) if uchar : uart.writechar(uchar[0]...
by chrisPyres66
Wed Dec 05, 2018 2:28 am
Forum: Technical Discussion
Topic: Standby consumption
Replies: 16
Views: 3291

Re: Standby consumption

Thanks for your answer What kind of high efficient SMPS you use and have you replace the regulator of the M7 camera with it ? I found that there is no pull resistor on OV7725 PWDN pin. I see 500uA by adding 4.7K Ohm pull up on OV7725 PWDN ( PCB pattern is covered. so need to scratch off printed ink ...
by chrisPyres66
Tue Dec 04, 2018 10:41 am
Forum: Technical Discussion
Topic: low power waiting for uart rx
Replies: 4
Views: 1401

low power waiting for uart rx

Hello, I would like to optimize consumption during the time the cpu wait the uart receipt. I wrote below the different way and names i found on internet documentation about : STM32 ------------ machine ---------- pyb --------------- time sleep ---------------- idle ------------ wfi ---------- time.s...
by chrisPyres66
Tue Dec 04, 2018 9:15 am
Forum: Technical Discussion
Topic: Use of callback function in sleep mode
Replies: 6
Views: 1695

Re: Use of callback function in sleep mode

Ok, you are right i should do :

Code: Select all

git checkout .
git pull
i confirm callback funtion in sleep and deepsleep mode
Thanks,

Go to advanced search