TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi icon indicating copy to clipboard operation
TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi copied to clipboard

A tutorial showing how to train, convert, and run TensorFlow Lite object detection models on Android devices, the Raspberry Pi, and more!

Results 83 TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi issues
Sort by recently updated
recently updated
newest added
trafficstars

Hi, I have A project where I am trying to retrain an object detector to detect 3 different object classes within an image taken from a USB camera on a...

Hello the tutorial and code have been working great. I have been able to create custom models with Google's AutoML export them to TFLite and then run them. On my...

I managed to convert .pb file of Faster RCNN to .tflite. But while testing the detection code it gives " list index out of range" error CODE - import tensorflow...

Hi all, I followed the tutorial entirely, successfully trained my custom ssd_mobilenet_v2_quantized_300x300_coco model with 7 classes to detect. The issue comes when I try to run the webcam detection script,...

A nice project with detailed instructions. Even though TensorFlow Lite on Android is straightforward using the google example, but that does not include using IP Cam stream for TFlite models....

(tensorflow1) C:\tensorflow1\models\research\object_detection>python train.py --logtostderr -train_dir=training/ --pipeline_config_path=training/ssd_mobilenet_v2_quantized_300x300_coco.config 2021-06-18 19:48:25.922052: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'cudart64_101.dll'; dlerror: cudart64_101.dll not found 2021-06-18 19:48:25.922247: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you...

python3 TFLite_detection_webcam.py --modeldir=model Traceback (most recent call last): File "TFLite_detection_webcam.py", line 138, in interpreter = Interpreter(model_path=PATH_TO_CKPT) File "/home/pi/TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi/tflite-env/lib/python3.7/site-packages/tflite_runtime/interpreter.py", line 207, in __init__ custom_op_registerers_by_func)) ValueError: Model provided has model identifier 'norm',...

Replace: python TFLite_detection_image.py --modeldir=TFLite_model --video='birdy.mp4' with: python TFLite_detection_video.py --modeldir=TFLite_model --video='birdy.mp4'

Guys, If you search a version for yolov4-tiny, you can find [here](https://github.com/GiorgioSgl/TFLite_Yolov4_and_SSD) a version implemented with also some improvemenents in general. You can find already the yolov4 weights converted for...

why when i run num = interpreter.get_tensor(output_details[3]['index'])[0] its always return "10" number?