Martin Kersner
Martin Kersner
@chl916185 I think it works only with Tensorflow 1.4.
Hi @fkromer ! Thank you for contributing! I created new section MCU and MPU software packages. https://github.com/Bisonai/awesome-edge-machine-learning#mcu-and-mpu-software-packages
Hello @joshisr10, Thank you for reaching out! Have you tried to run the code with TensorFlow 1.13? Cheers, Martin
Hi @fzyzcjy! We are planning to share pretrained weights, but currently, we do not have them. Cheers, Martin
Hi @caocuong0306 ! When do you set the `learning phase`? Before or after the model is created? We use ` tf.keras.backend.set_learning_phase` at the beginning of script in our other project...
Hi @dreamitpossible1! The repository provides model definitions and basic training script so you can train mobilenetv3. What exact problem did you have? Cheers, Martin
Thank you for bringing on-device training to TFLite! Based on this proposal I am not sure where do you plan to manage a training loop. Are you thinking of (1)...
It works under Python 2, but you have to replace following line (occurs 3 times) ``` python line = process.stdout.readline() ``` with ``` python line = process.communicate()[0] ``` in _models.py_....
I checked how you integrated my suggestion and it turned it you didn't do it at all. For those who are still having difficulties, you can try out my fork...
@jonkoi You are right, the implementation is not correct. The first two ABC layers behave only as constant feature extractors and all the learning happens in the last two float...