TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi

TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi copied to clipboard

Hello, I wanna train my custom model that only detect persons. Python file(train.py) successfully works, but loss is not. Now, it is over 140,000 steps, loss is still over 2.(Sometimes...

JSP-ywu

I have a webcam running on the Pi - Is there a way to use that stream as the source for TF

3

I was wondering if you could direct me to using your tutorial with an existing video stream. I have a webcam running on the Pi - Is there a way...

rcpilotp51

Hey! I was wondering if there is a way to integrate tracking into this. I have found some repositories about tracking off the MS COCO dataset, but I am looking...

jp3spinelli

Tensorflow build from source FAIL

1

I followed the guide exactly, installed Microsoft Build Tools 2015 Update 3, and also the Microsoft Visual C++ 2015 Redistributable Update 3. Tensorflow version is also the same(1.13) Now during...

aflat00n

connecting to HikVision cameras

3

Hi, I've install Tensorflow lite using you very well detailed guide, thank you for that. it is possible to connect to them hikvision my link i use within home assistant...

phairplay

Hi, when I downloaded the ssd_mobilenet_v2_quantized_300x300_coco_2019_01_03 model, there is no model.ckpt file. file list: model.ckpt.data-00000-of-00001 model.ckpt.index model.ckpt.meta pipeline.config tflite_graph.pb tflite_graph.pbtxt From where I can get this file?

MevadaRavikumar

How to improve FPS on raspberry pi?

1

I have deployed the object detection model to the raspberry pi, but the FPS is still small. How do I increase the FPS so that the model can be used...

talenta01

implementation the model to jetson nano

1

I want to deploy my detection object model to jetson nano but there is no good tutorial to follow. i tried to follow the raspberry pi tutorial but it didn't...

talenta01

This will solve the issue I had ""IndexError: child index out of range " Edit: for member in root.findall('object'): value = (root.find('filename').text, int(root.find('size').find('width').text), int(root.find('size').find('height').text), member[0].text, int(member.find("bndbox").find('xmin').text), int(member.find("bndbox").find('ymin').text), int(member.find("bndbox").find('xmax').text), int(member.find("bndbox").find('ymax').text) )

ET0E

Hello mantainers, the `calculate_map_cartucho.py` script doesn't work if already exist a `/content/mAP/outputs` file. This change remove this output before running the script for the quantized model.

lucasbernardestoradex