Search found 8 matches
- Thu Jan 07, 2021 12:36 am
- Forum: ESP32 Arduino
- Topic: ESP-Wrover B 8Mb Disabled?
- Replies: 0
- Views: 2884
ESP-Wrover B 8Mb Disabled?
Quick question, I've developed my own PCB board with the ESP32-Wrover B 8Mb module and it is working nicely! however, there is something odd with the board's PSRAM settings. In order for the board to enter the application-level code, I must disable PSRAM in the boot settings otherwise the board will...
- Thu Jan 09, 2020 8:31 am
- Forum: ESP-WHO
- Topic: How to create a custom object detection classifier
- Replies: 2
- Views: 19079
Re: How to create a custom object detection classifier
Hey, as an update I think i've figured out how to get custom object detection working
( the code has a few bugs that I'm working out, but the model does run)
code is found here:
https://github.com/caleb221/ESP32-Leaf
( the code has a few bugs that I'm working out, but the model does run)
code is found here:
https://github.com/caleb221/ESP32-Leaf
- Mon Dec 30, 2019 5:35 pm
- Forum: Sample Code
- Topic: ESP-FACE MTCNN custom object detection
- Replies: 0
- Views: 8764
ESP-FACE MTCNN custom object detection
Hey!
I've made an implementation of MTCNN using the ESP-FACE library.
If anyone is interested in taking a look it can be found here https://github.com/caleb221/ESP32-Leaf
*** it still has some bugs I'm working out, but the model does run ****
Thanks!
-Caleb
I've made an implementation of MTCNN using the ESP-FACE library.
If anyone is interested in taking a look it can be found here https://github.com/caleb221/ESP32-Leaf
*** it still has some bugs I'm working out, but the model does run ****
Thanks!
-Caleb
- Tue Dec 03, 2019 8:07 pm
- Forum: ESP-IDF
- Topic: How to change from face detection to other own trained object detection
- Replies: 1
- Views: 3726
Re: How to change from face detection to other own trained object detection
what kind of SVM are you using?
There are a few arduino SVM libraries that might suit your needs
(i dont have the names but i was looking through options awhile back and i did see there were a few)
There are a few arduino SVM libraries that might suit your needs
(i dont have the names but i was looking through options awhile back and i did see there were a few)
- Tue Dec 03, 2019 12:37 pm
- Forum: ESP-WHO
- Topic: Building a new classifier for the ESP WHO
- Replies: 5
- Views: 19331
Re: Building a new classifier for the ESP WHO
If anyone is familiar with this framework, I am currently testing an implementation of MTCNN.
I am at this point with the code and am having a NaN issue.
more details explained here:
https://github.com/espressif/esp-face/issues/17
Thanks!
-Caleb
I am at this point with the code and am having a NaN issue.
more details explained here:
https://github.com/espressif/esp-face/issues/17
Thanks!
-Caleb
- Tue Nov 05, 2019 8:34 am
- Forum: ESP-WHO
- Topic: How to create a custom object detection classifier
- Replies: 2
- Views: 19079
Re: How to create a custom object detection classifier
hey, so i'm still a bit lost on this as well (im very new to deep learning) from my understanding you need to train the model using whatever you like (tensorflow, pytorch, whatever..) to get your inference graph...once you have that its when you build the model in C for the ESP you can use a lot of ...
- Mon Jul 29, 2019 8:30 am
- Forum: ESP-WHO
- Topic: Building a new classifier for the ESP WHO
- Replies: 5
- Views: 19331
Re: Building a new classifier for the ESP WHO
Ok Great! Thank you!
Also, i appreciate the quick reply
Thanks again!
-Caleb
Also, i appreciate the quick reply
Thanks again!
-Caleb
- Sun Jul 28, 2019 1:48 pm
- Forum: ESP-WHO
- Topic: Building a new classifier for the ESP WHO
- Replies: 5
- Views: 19331
Building a new classifier for the ESP WHO
Hello! I have been reading through the open sourced documentation on GitHub as well as the libraries that have been developed. I understand that the MTMN face detection model is being used on the ESP32 and it is specially designed for facial recognition. My question would be what were the steps take...