Exportar modelos YOLO26 al formato TFLite Edge TPU
Desplegar modelos de visión artificial en dispositivos con poca potencia de cálculo, como móviles o sistemas integrados, puede ser complicado. El uso de un formato de modelo optimizado para un mayor rendimiento simplifica el proceso. El formato de modelo TensorFlow Lite Edge TPU, o TFLite Edge TPU, está diseñado para consumir poca energía y ofrecer un alto rendimiento en redes neuronales.
Exportar al formato TFLite Edge TPU te permite optimizar tus modelos Ultralytics YOLO26 para lograr una inferencia rápida y de bajo consumo. En esta guía te explicamos cómo convertir tus modelos al formato TFLite Edge TPU para que funcionen mejor en distintos dispositivos móviles y sistemas integrados.
¿Por qué exportar al formato TFLite Edge TPU?#
Exportar modelos a TensorFlow Edge TPU permite ejecutar tareas de aprendizaje automático de forma rápida y eficiente. Esta tecnología es adecuada para aplicaciones con limitaciones de energía, recursos de cálculo y conectividad. Edge TPU es la versión edge del acelerador de hardware unidad de procesamiento tensorial (TPU) de Google. Acelera los modelos TensorFlow Lite en dispositivos edge. La imagen siguiente muestra un ejemplo del proceso.
Edge TPU funciona con modelos cuantizados. La cuantización reduce el tamaño de los modelos y los acelera sin perder demasiada precisión. Es ideal para los recursos limitados de la computación edge: permite que las aplicaciones respondan rápidamente, reduce la latencia y facilita el procesamiento local de datos sin depender de la nube. El procesamiento local también mantiene los datos de los usuarios privados y seguros, ya que no se envían a un servidor remoto.
Características principales de TFLite Edge TPU#
Estas son las principales características que convierten TFLite Edge TPU en una excelente opción de formato de modelo para desarrolladores:
-
Rendimiento optimizado en dispositivos edge: TFLite Edge TPU ofrece una inferencia rápida de redes neuronales mediante cuantización, optimización de modelos, aceleración por hardware y optimización del compilador. Su arquitectura minimalista contribuye a reducir su tamaño y coste.
-
Alto rendimiento computacional: TFLite Edge TPU combina aceleración de hardware especializada y una ejecución eficiente para lograr un alto rendimiento computacional. Es muy adecuado para implementar modelos de aprendizaje automático con requisitos de rendimiento estrictos en dispositivos periféricos.
-
Cálculos matriciales eficientes: TensorFlow Edge TPU está optimizado para operaciones matriciales, fundamentales para los cálculos de redes neuronales. Esta eficiencia es clave en los modelos de aprendizaje automático, especialmente en aquellos que requieren numerosas multiplicaciones y transformaciones matriciales complejas.
Opciones de implementación con TFLite Edge TPU#
Antes de exportar modelos YOLO26 al formato TFLite Edge TPU, conviene entender para qué se suelen utilizar.
TFLite Edge TPU ofrece varias opciones para implementar modelos de aprendizaje automático, entre ellas:
-
Implementación en el dispositivo: Los modelos TensorFlow Edge TPU se pueden implementar directamente en dispositivos móviles e integrados. La implementación en el dispositivo permite ejecutar los modelos directamente en el hardware, sin necesidad de conectarse a la nube, ya sea integrando el modelo en el paquete de la aplicación o descargándolo cuando se necesite.
-
Implementación híbrida: Un enfoque híbrido combina la implementación en el dispositivo y en la nube, y ofrece una solución versátil y escalable para implementar modelos de aprendizaje automático. Entre sus ventajas se incluyen el procesamiento en el dispositivo para obtener respuestas rápidas y la computación en la nube para realizar cálculos más complejos.
Tareas compatibles#
La exportación a Edge TPU es compatible con seis de las siete tareas de Ultralytics. La segmentación semántica solo está disponible con YOLO26, la única familia que incluye esa cabeza. La estimación de profundidad no es compatible porque su modelo INT8 genera un operador v2 EXP que el compilador de Edge TPU no puede analizar.
| Tarea | YOLOv8 | YOLO11 | YOLO26 |
|---|---|---|---|
| Detectar | ✅ | ✅ | ✅ |
| Segmentar | ✅ | ✅ | ✅ |
| Semántica | ❌ | ❌ | ✅ |
| Profundidad | ❌ | ❌ | ❌ |
| Clasificar | ✅ | ✅ | ✅ |
| Pose | ✅ | ✅ | ✅ |
| OBB | ✅ | ✅ | ✅ |
El compilador de Edge TPU asigna las operaciones compatibles al acelerador y deja el resto en la CPU, por lo que la compatibilidad con una tarea no significa que todas sus operaciones se ejecuten en la TPU.
Exportar modelos YOLO26 a TFLite Edge TPU#
Puedes ampliar la compatibilidad de los modelos y la flexibilidad de implementación convirtiendo modelos YOLO26 a TensorFlow Edge TPU.
Instalación#
Para instalar el paquete necesario, ejecuta:
# Install the required package for YOLO26
pip install ultralyticsPara obtener instrucciones detalladas y buenas prácticas relacionadas con el proceso de instalación, consulta nuestra guía de instalación de Ultralytics. Si tienes dificultades al instalar los paquetes necesarios para YOLO26, consulta nuestra guía sobre problemas habituales, donde encontrarás soluciones y consejos.
Uso#
Todos los modelos Ultralytics YOLO26 están diseñados para admitir la exportación desde el primer momento, lo que facilita su integración en el flujo de trabajo de implementación que prefieras. Puedes consultar la lista completa de formatos de exportación y opciones de configuración compatibles para elegir la configuración más adecuada para tu aplicación.
El formato TFLite Edge TPU es compatible con los modos Exportar, Predecir y Validar. La inferencia y la validación se ejecutan en hardware Coral Edge TPU. Exporta tu modelo y, a continuación, carga el modelo exportado para ejecutar inferencias o validar su precisión.
from ultralytics import YOLO
# Carga un modelo YOLO26
model = YOLO("yolo26n.pt")
# Exporta el modelo al formato TFLite Edge TPU
model.export(format="edgetpu") # crea 'yolo26n_saved_model/yolo26n_full_integer_quant_edgetpu.tflite'from ultralytics import YOLO
# Carga el modelo TFLite Edge TPU exportado
model = YOLO("yolo26n_saved_model/yolo26n_full_integer_quant_edgetpu.tflite")
# Ejecutar inferencia
results = model("https://ultralytics.com/images/bus.jpg")from ultralytics import YOLO
# Carga el modelo TFLite Edge TPU exportado
model = YOLO("yolo26n_saved_model/yolo26n_full_integer_quant_edgetpu.tflite")
# Valida la precisión con el conjunto de datos COCO8
metrics = model.val(data="coco8.yaml")Argumentos de exportación#
| Argumento | Tipo | Predeterminado | Descripción |
|---|---|---|---|
format | str | 'edgetpu' | Formato de destino del modelo exportado, que define su compatibilidad con distintos entornos de implementación. |
imgsz | int o tuple | 640 | Tamaño de imagen deseado para la entrada del modelo. Puede ser un número entero para imágenes cuadradas o una tupla (height, width) para dimensiones específicas. |
quantize | int o str | 8/auto | Precisión de cuantización. 8 (INT8) es obligatorio y se activa automáticamente para Edge TPU; comprime el modelo y acelera la inferencia con una pérdida mínima de precisión en dispositivos edge. Sustituye a las opciones obsoletas half/int8. |
opset | int | None | Especifica la versión del opset de ONNX para el grafo ONNX intermedio. Si no se establece, se usa el opset 18 (inferior en PyTorch < 2.4), limitado a la versión instalada de onnx. |
data | str | None | Ruta al archivo YAML del conjunto de datos, imprescindible para la cuantización; en clasificación, en su lugar se indica un directorio del conjunto de datos o el nombre de un conjunto de datos integrado. Si se omite con quantize=8, Ultralytics selecciona el conjunto de datos de calibración predeterminado para la tarea del modelo. |
fraction | float, int o list | 1.0 | Subconjunto de calibración expresado como proporción, número de imágenes o proporciones/recuentos [train, val, test]. Las listas de dos elementos dejan completo test, mientras que 0 lo omite. |
device | str | None | Especifica el dispositivo para la exportación: CPU (device=cpu). |
Usa una máquina Linux x86 para exportar a Edge TPU.
Para obtener más información sobre el proceso de exportación, visita la página de documentación de Ultralytics sobre exportación.
Implementar modelos YOLO26 TFLite Edge TPU exportados#
Tras exportar correctamente tus modelos Ultralytics YOLO26 al formato TFLite Edge TPU, ya puedes desplegarlos. El primer paso recomendado para ejecutar un modelo TFLite Edge TPU es usar el método YOLO("model_edgetpu.tflite"), como se muestra en el fragmento de código de uso anterior.
Sin embargo, si necesitas instrucciones detalladas para implementar tus modelos TFLite Edge TPU, consulta los siguientes recursos:
-
Coral Edge TPU en una Raspberry Pi con Ultralytics YOLO26: Descubre cómo integrar Coral Edge TPU con Raspberry Pi para mejorar las capacidades de aprendizaje automático.
-
Compilador Edge TPU: descubre cómo el compilador Edge TPU asigna modelos TensorFlow Lite al acelerador y qué operaciones admite.
-
Ejecutar inferencias en Edge TPU con Python: Descubre cómo usar la API de Python de TensorFlow Lite para aplicaciones Edge TPU, con indicaciones de configuración y uso.
Resumen#
En esta guía hemos aprendido a exportar modelos Ultralytics YOLO26 al formato TFLite Edge TPU. Si sigues los pasos anteriores, podrás ejecutar tus aplicaciones de visión artificial más rápido y con menos consumo en dispositivos edge.
Para obtener más información sobre el uso, visita el sitio web oficial de Coral Edge TPU.
Preguntas frecuentes#
Para exportar un modelo YOLO26 al formato TFLite Edge TPU, sigue estos pasos:
Usofrom ultralytics import YOLO # Carga un modelo YOLO26 model = YOLO("yolo26n.pt") # Exporta el modelo al formato TFLite Edge TPU model.export(format="edgetpu") # crea 'yolo26n_saved_model/yolo26n_full_integer_quant_edgetpu.tflite' # Carga el modelo TFLite Edge TPU exportado edgetpu_model = YOLO("yolo26n_saved_model/yolo26n_full_integer_quant_edgetpu.tflite") # Ejecutar inferencia results = edgetpu_model("https://ultralytics.com/images/bus.jpg")Para obtener todos los detalles sobre cómo exportar modelos a otros formatos, consulta nuestra guía de exportación.
Exportar modelos YOLO26 a TFLite Edge TPU ofrece varias ventajas:
- Rendimiento optimizado: Consigue un alto rendimiento de las redes neuronales con un consumo mínimo de energía.
- Menor latencia: Procesa los datos localmente con rapidez, sin depender de la nube.
- Mayor privacidad: El procesamiento local mantiene los datos de los usuarios privados y seguros.
Esto lo hace ideal para aplicaciones de computación edge, donde los dispositivos tienen recursos de cálculo y energía limitados.
Sí, los modelos TensorFlow Lite Edge TPU se pueden implementar directamente en dispositivos móviles e integrados. Este enfoque permite ejecutar los modelos directamente en el hardware, con inferencias más rápidas y eficientes. Para ver ejemplos de integración, consulta nuestra guía para implementar Coral Edge TPU en Raspberry Pi.
Entre los casos de uso habituales de los modelos TFLite Edge TPU se incluyen:
- Cámaras inteligentes: Mejoran el análisis de imágenes y vídeos en tiempo real.
- Dispositivos IoT: Hacen posible la automatización del hogar inteligente y de la industria.
- Sanidad: Aceleran el diagnóstico y el procesamiento de imágenes médicas.
- Comercio minorista: Mejoran la gestión del inventario y el análisis del comportamiento de los clientes.
Estas aplicaciones se benefician del alto rendimiento y el bajo consumo de energía de los modelos TFLite Edge TPU. Descubre más escenarios de uso.
Si tienes problemas al exportar o implementar modelos TFLite Edge TPU, consulta nuestra guía de problemas habituales para obtener consejos de resolución. Esta guía abarca problemas comunes y sus soluciones para ayudarte a garantizar un funcionamiento correcto. Si necesitas más ayuda, visita nuestro Centro de ayuda.
Comentarios30
Haz una pregunta, comparte tus resultados o ayuda a otra persona.
faizaanscnz
I am running a float32 TFLite model on Pixel 8a using the GPU. How can I run an Edge TPU model on the hardware to get faster FPS? I’m currently getting 8 FPS, but I need 20+. (Kivy app)
walissong
I would like to know if this tutorial works with yolov8n. I've been trying for many days and I'm not able to convert it to edgetpu.tflite.
dbro
Hello. This seems to be broken for yolo11, although it works for yolov8. After running these two commands in Google colab, the output file is less than 1kb and it generates an error.
! pip install ultralytics ! yolo mode=export model=yolo11n.pt format=edgetpu imgsz=320
The final step to run the EdgeTPU compiler seems to be where the problem is:
... TensorFlow SavedModel: export success ✅ 112.9s, saved as 'yolo11n_saved_model' (33.8 MB)
Edge TPU: starting export with Edge TPU compiler 16.0.384591198... Edge TPU: running 'edgetpu_compiler --out_dir "yolo11n_saved_model" --show_operations --search_delegate --delegate_search_step 30 --timeout_sec 180 "yolo11n_saved_model/yolo11n_full_integer_quant.tflite"' Edge TPU Compiler version 16.0.384591198 Searching for valid delegate with step 30 Try to compile segment with 677 ops ERROR: Didn't find op for builtin opcode 'CONV_2D' version '6'. An older version of this builtin might be supported. Are you using an old TFLite binary with a newer model?
ERROR: Registration failed.
Invalid model: yolo11n_saved_model/yolo11n_full_integer_quant.tflite Model could not be parsed Edge TPU: export success ✅ 0.0s, saved as 'yolo11n_saved_model/yolo11n_full_integer_quant_edgetpu.tflite' (0.0 MB) ...
tomcomtang
I am still studying edge computing(https://edgeone.ai/learning/edge-computing), while you have already delved into a deeper level.
Glenn JocherUltralytics@tomcomtang yes, TFLite Edge TPU is designed for optimized performance in edge computing, offering high-speed neural networking with minimal power, reduced latency, and enhanced privacy. For details see the TFLite Edge TPU docs: https://docs.ultralytics.com/integrations/edge-tpu/
manu13008
Hi, Once I exported my best.pt model into edgetpu tflite, I tried to run an inference on an image as the code above but I got the following error :
OSError: libedgetpu.so.1: cannot open shared object file: No such file or directory
Do you have any insights of how resolving this ?
Thanks :)
Glenn JocherUltralytics@manu13008 it seems like the error is due to the missing Edge TPU runtime library. Please ensure you have installed the Edge TPU runtime on your device. You can find installation instructions in the Edge TPU documentation. If you need further assistance, feel free to check the resources there.
Abdullah-Ory
Hi friends, i am using google colap to compile yolo11n.pt into edgetpu format, since i have orange pi 5 pro which is arm, so when i am trying to do it in my laptop i got this Ultralytics 8.3.9 🚀 Python-3.10.12 torch-2.4.1+cu121 CPU (Intel Xeon 2.20GHz) YOLO11n summary (fused): 238 layers, 2,616,248 parameters, 0 gradients, 6.5 GFLOPs
PyTorch: starting from '/content/yolo11n.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 84, 8400) (5.4 MB)
TensorFlow SavedModel: starting export with tensorflow 2.17.0...
ONNX: starting export with onnx 1.17.0 opset 19... ONNX: slimming with onnxslim 0.1.34... ONNX: export success ✅ 3.0s, saved as '/content/yolo11n.onnx' (10.3 MB) TensorFlow SavedModel: starting TFLite export with onnx2tf 1.22.3...
Automatic generation of each OP name started ======================================== Automatic generation of each OP name complete!
Model loaded ========================================================================
Model conversion started ============================================================ saved_model output started ========================================================== saved_model output complete! Float32 tflite output complete! Float16 tflite output complete! Dynamic Range Quantization tflite output complete! Input signature information for quantization signature_name: serving_default input_name.0: images shape: (1, 640, 640, 3) dtype: <dtype: 'float32'> INT8 Quantization tflite output complete! Full INT8 Quantization tflite output complete! Traceback (most recent call last): File "/usr/local/lib/python3.10/dist-packages/onnx2tf/onnx2tf.py", line 1566, in convert tflite_model = converter.convert() File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/lite.py", line 1231, in wrapper return self._convert_and_export_metrics(convert_func, *args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/lite.py", line 1183, in _convert_and_export_metrics result = convert_func(self, *args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/lite.py", line 1562, in convert return self._convert_from_saved_model(graph_def) File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/lite.py", line 1424, in _convert_from_saved_model return self._optimize_tflite_model( File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/convert_phase.py", line 215, in wrapper raise error from None # Re-throws the exception. File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/convert_phase.py", line 205, in wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/lite.py", line 1127, in _optimize_tflite_model model = self._quantize( File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/lite.py", line 767, in _quantize return calibrate_quantize.calibrate_and_quantize( File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/convert_phase.py", line 215, in wrapper raise error from None # Re-throws the exception. File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/convert_phase.py", line 205, in wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/optimize/calibrator.py", line 194, in calibrate_and_quantize return self._calibrator.QuantizeModel( RuntimeError: Quantized dimension for tensor property and quantization parameters do not match. Got 3 and 0 respectively.
WARNING: INT8 Quantization with int16 activations tflite output failed. Traceback (most recent call last): File "/usr/local/lib/python3.10/dist-packages/onnx2tf/onnx2tf.py", line 1597, in convert tflite_model = converter.convert() File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/lite.py", line 1231, in wrapper return self._convert_and_export_metrics(convert_func, *args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/lite.py", line 1183, in _convert_and_export_metrics result = convert_func(self, *args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/lite.py", line 1562, in convert return self._convert_from_saved_model(graph_def) File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/lite.py", line 1424, in _convert_from_saved_model return self._optimize_tflite_model( File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/convert_phase.py", line 215, in wrapper raise error from None # Re-throws the exception. File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/convert_phase.py", line 205, in wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/lite.py", line 1127, in _optimize_tflite_model model = self._quantize( File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/lite.py", line 767, in _quantize return calibrate_quantize.calibrate_and_quantize( File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/convert_phase.py", line 215, in wrapper raise error from None # Re-throws the exception. File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/convert_phase.py", line 205, in wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/tensorflow/lite/python/optimize/calibrator.py", line 194, in calibrate_and_quantize return self._calibrator.QuantizeModel( RuntimeError: Quantized dimension for tensor property and quantization parameters do not match. Got 3 and 0 respectively.
WARNING: Full INT8 Quantization with int16 activations tflite output failed. TensorFlow SavedModel: export success ✅ 248.1s, saved as '/content/yolo11n_saved_model' (36.1 MB) Edge TPU: WARNING ⚠️ Edge TPU known bug https://github.com/ultralytics/ultralytics/issues/1185
Edge TPU: starting export with Edge TPU compiler 16.0.384591198... Edge TPU: running 'edgetpu_compiler -s -d -k 10 --out_dir "/content/yolo11n_saved_model" "/content/yolo11n_saved_model/yolo11n_full_integer_quant.tflite"' Edge TPU: export success ✅ 3.9s, saved as '/content/yolo11n_saved_model/yolo11n_full_integer_quant_edgetpu.tflite' (3.5 MB)
Export complete (252.6s) Results saved to /content Predict: yolo predict task=detect model=/content/yolo11n_saved_model/yolo11n_full_integer_quant_edgetpu.tflite imgsz=640 int8 Validate: yolo val task=detect model=/content/yolo11n_saved_model/yolo11n_full_integer_quant_edgetpu.tflite imgsz=640 data=/usr/src/ultralytics/ultralytics/cfg/datasets/coco.yaml int8 Visualize: https://netron.app /content/yolo11n_saved_model/yolo11n_full_integer_quant_edgetpu.tflite
Glenn JocherUltralytics@Abdullah-Ory it seems you're encountering an issue with INT8 quantization during the TFLite Edge TPU export. Please ensure your model is compatible with Edge TPU requirements, and consider checking the Ultralytics documentation for detailed guidance on exporting models to TFLite Edge TPU format. If the issue persists, reviewing the quantization parameters might help.
MECHAAMER
Hi,
I trained a YOLOv8l model with VisDrone dataset, and attempted to convert the best weights.pt to Edge TPU TFlite format using:
model = YOLO("best.pt") model.export(format="edgetpu")
my board is Coral dev board.
The conversion completed successfully, but the results indicate that 164 of operations will run on the CPU instead of the Edge TPU. only 223 operation will run using Edge TPU This CPU usage will likely cause performance delays.
I'm wondering if there are any strategies or techniques to improve Edge TPU utilization and minimize CPU usage during inference for this model. Any suggestions or insights would be greatly appreciated.
Thanks,
Glenn JocherUltralytics@MECHAAMER to improve Edge TPU utilization, ensure your model is fully quantized and compatible with Edge TPU operations. Consider simplifying the model architecture or using supported operations. For detailed guidance, please refer to the Ultralytics Edge TPU documentation.
MECHAAMER
Hi, thank you for your support, I follow the attached link, and apply it using: model.export(format="edgetpu") , and I get this output:
Number of operations that will run on Edge TPU: 133 Number of operations that will run on CPU: 364
more details in the attached photo.
I think with this big percent of ops that runs on the CPU, the model will be very slow and I will suffer from large latency.
Do you have any suggestions?
Glenn JocherUltralyticsTo improve Edge TPU utilization, ensure your model is fully quantized and uses supported operations. Simplifying the model architecture might help. For more details, please refer to the Ultralytics Edge TPU documentation.
MECHAAMER
Hi there,
I'm following the Ultralytics Edge TPU documentation to train a YOLO model for object detection. However, I'm encountering suboptimal results.
I suspect that the issue might lie in the model's compatibility with the TPU. It's possible that certain operations within the model are not optimized for the TPU, leading to delays.
To address this, I'm considering using a YOLO model that is specifically designed to run efficiently on the Edge TPU. Do you have any recommendations for such models?
Glenn JocherUltralyticsFor optimal Edge TPU performance, consider using a smaller YOLO model like YOLOv8n, which is more compatible with Edge TPU operations. Simplifying the model architecture can also help.
MECHAAMER
I'm encountering a "Segmentation fault" error while trying to run a segmented YOLOv5s model on my Coral Dev Board with an external Coral ML Accelerator (USB). I followed the recommended steps to export, compile, and segment the model using edgetpu_compiler.
I follow these steps:
I trained Yolov5su model, then I exported the model as tflite - 8int by using: model.export() then I use the edgetpu_compiler to compile the tflite model and segmented it into 2 models: edgetpu_compiler model.tflite --num_segments=2 then I get 12 files, 8 models and 4 logs, the models are: 1- best_float32_segment_0_of_2.tflite 2- best_float32_segment_1_of_2.tflite 3- best_float32_segment_0_of_2_edgetpu.tflite 4- best_float32_segment_1_of_2_edgetpu.tflite 5- best_full_integer_quant_segment_0_of_2.tflite 6- best_full_integer_quant_segment_1_of_2.tflite 7- best_full_integer_quant_segment_0_of_2_edgetpu.tflite 8- best_full_integer_quant_segment_1_of_2_edgetpu.tfliteI transfer the "best_full_integer_quant_segment_0_of_2_edgetpu.tflite" and "best_full_integer_quant_segment_1_of_2_edgetpu.tflite" to the coral board and I tried to run the models to detect object in a video, the code:
import argparse import re import threading import time import numpy as np import cv2 from pycoral.adapters import classify from pycoral.adapters import common import pycoral.pipeline.pipelined_model_runner as pipeline from pycoral.utils.dataset import read_label_file from pycoral.utils.edgetpu import list_edge_tpus from pycoral.utils.edgetpu import make_interpreter def _get_devices(num_devices): edge_tpus = list_edge_tpus() if len(edge_tpus) < num_devices: raise RuntimeError( 'Not enough Edge TPUs detected, expected %d, detected %d.' % (num_devices, len(edge_tpus))) num_pci_devices = sum(1 for device in edge_tpus if device['type'] == 'pci') return ['pci:%d' % i for i in range(min(num_devices, num_pci_devices))] + [ 'usb:%d' % i for i in range(max(0, num_devices - num_pci_devices)) ] def _make_runner(model_paths, devices): """Constructs PipelinedModelRunner given model paths and devices.""" print('Using devices: ', devices) print('Using models: ', model_paths) print(" hey runner 1") if len(model_paths) != len(devices): raise ValueError('# of devices and #of model_paths should match') print(" hey runner 2", model_paths[0], devices[1]) interpreters = [] interpreter = make_interpreter(model_paths[0], devices[0]) print(" hey runner 3") interpreter.allocate_tensors() print(" hey runner 4") interpreters.append(interpreter) print(" hey runner 5", model_paths[1], devices[0]) interpreter2 = make_interpreter(model_paths[1], devices[1]) print(" hey runner 6") interpreter.allocate_tensors() interpreter2.allocate_tensors() print(" hey runner 7") interpreters.append(interpreter2) print(" hey runner 8") return pipeline.PipelinedModelRunner(interpreters) def main(): parser = argparse.ArgumentParser( formatter_class=argparse.ArgumentDefaultsHelpFormatter) parser.add_argument( '-m', '--models', required=True, help=('File path template of .tflite model segments, e.g.,' 'inception_v3_299_quant_segment_%d_of_2_edgetpu.tflite')) parser.add_argument( '-i', '--input', required=True, help='Image to be classified.') parser.add_argument('-l', '--labels', help='File path of labels file.') parser.add_argument( '-k', '--top_k', type=int, default=1, help='Max number of classification results') parser.add_argument( '-t', '--threshold', type=float, default=0.0, help='Classification score threshold') parser.add_argument( '-c', '--count', type=int, default=1, help='Number of times to run inference') args = parser.parse_args() labels = {0:"pedestrian", 1:"people", 2:"bicycle", 3:"car", 4:"van", 5:"truck", 6:"tricycle", 7:"awning-tricycle", 8:"bus", 9:"motor"} print("hey lets begin 1") result = re.search(r'^.*_segment_%d_of_(?P<num_segments>[0-9]+)_.*.tflite', args.models) print("hey lets begin 2") if not result: print("hey lets begin 3") raise ValueError( '--models should follow *_segment%d_of_[num_segments]_*.tflite pattern') print("hey lets begin 4") num_segments = int(result.group('num_segments')) model_paths = [args.models % i for i in range(num_segments)] print("hey lets begin 5") devices = _get_devices(num_segments) print("hey lets begin 6") runner = _make_runner(model_paths, devices) print("hey lets begin 7") # Get the input name and size size = common.input_size(runner.interpreters()[0]) print("hey lets begin 8") name = common.input_details(runner.interpreters()[0], 'name') print("hey lets begin 9") cap = cv2.VideoCapture(args.input) print("hey lets begin 10") if not cap.isOpened(): print("Error opening video capture device") return print("hey lets begin 11") while True: ret, frame = cap.read() if not ret: break # Preprocess the frame height, width, _ = frame.shape new_height = int(640 * height / width) image = cv2.resize(frame, (640, new_height)) # Run inference runner.push({name: image}) output_details = runner.interpreters()[-1].get_output_details()[0] scale, zero_point = output_details['quantization'] result = runner.pop() if result: # Process the results values, = result.values() scores = scale * (values[0].astype(np.int64) - zero_point) classes, scores = classify.get_classes_from_scores(result[0], args.top_k, args.threshold) for klass in classes: print('%s: %.5f' % (labels.get(klass.id, klass.id), klass.score)) print('-------RESULTS--------') else: print("No results") if __name__ == '__main__': main()then I try execute the python file:python3 test2tpu.py -m best_full_integer_quant_segment_%d_of_2_edgetpu.tflite -i "/coral/720p/Busy Road.mp4"
the output that I get:
hey lets begin 1 hey lets begin 2 hey lets begin 4 hey lets begin 5 hey lets begin 6 Using devices: ['pci:0', 'usb:0'] Using models: ['best_full_integer_quant_segment_0_of_2_edgetpu.tflite', 'best_full_integer_quant_segment_1_of_2_edgetpu.tflite'] hey runner 1 hey runner 2 best_full_integer_quant_segment_0_of_2_edgetpu.tflite usb:0 hey runner 3 hey runner 4 hey runner 5 best_full_integer_quant_segment_1_of_2_edgetpu.tflite pci:0 Segmentation fault
Note: pycoral version: 2.0.0
Glenn JocherUltralyticsIt seems like the segmentation fault might be due to compatibility issues with the model operations on the Edge TPU. Consider simplifying the model architecture or ensuring all operations are supported by the Edge TPU. You can also check the Common Issues guide for additional troubleshooting tips.
MECHAAMER
Can you help me to know more about: simplifying the model architecture or ensuring all operations are supported by the Edge TPU.
I don't have access now to the records because I am outside office, as I remember In yolov5su, there are more than 200 process depends in TPU and only 25 process use CPU, Also the model working well on 1 TPU (with no segmentation).
Glenn JocherUltralytics@MECHAAMER to improve Edge TPU compatibility, consider using a smaller model like YOLOv8n, which is more likely to use supported operations, or simplify the architecture by reducing layers and operations that are not TPU-optimized.
Taufiq-Ahmed
Hi, I have train my custom dataset for detect fire and smoke with yolov8 nano. it's best model size is around 6MB and after exporting it using "yolo export model=yolov8n.pt format=edgetpu". it's size reduced to 3MB. But have to integrate this model in XIAO RP2040 MCU. So I need more light weight model for my edge device. In this case what I should? Please give me a solution.
Glenn JocherUltralytics@Taufiq-Ahmed hi! It's great to hear that you've successfully trained your custom dataset with YOLOv8 nano. For further reducing the model size for your XIAO RP2040 MCU, you might want to explore additional quantization techniques. The TFLite Edge TPU format already applies full integer quantization, but you can experiment with pruning or other model compression techniques to further reduce the size. If you haven't already, ensure you're using the latest version of the Ultralytics package for the best optimization features. For more detailed guidance, you can check out our Edge TPU integration guide. Good luck with your deployment!
samphonic
So I have a tflite model and object detection is working, but I can't seem to figure out how to tell if (and how effectively) the model is actually using the Edge TPU hardware. Is there some way to confirm that the hardware is actually being used? Can I manually enable/disable it to compare inference time?
Glenn JocherUltralytics@Sammy1Am to confirm if your model is utilizing the Edge TPU hardware, you can check the inference time and compare it with and without the Edge TPU. Typically, when the Edge TPU is in use, you should see a significant reduction in inference time. You can manually enable or disable the Edge TPU by using the
edgetpuinterpreter for the Edge TPU and the standard TFLite interpreter otherwise. For more details on setting this up, you might find the Edge TPU documentation helpful. If you need further assistance, feel free to explore our Ultralytics documentation.
FearL0rd
How do I use YOLO with a Dual TPU card?
I have APEX_0 and APEX_1 devices.
FearL0rd
Streamline segmentation during export https://coral.ai/docs/edgetpu/pipeline/
Glenn JocherUltralytics@FearL0rd thank you for your suggestion! Streamlining segmentation during export is indeed a valuable enhancement. For detailed guidance on exporting YOLOv8 models to TFLite Edge TPU format, you can refer to our documentation. This will help you optimize your models for high-speed, low-power inferencing on devices with limited computational power.
For more information on using YOLO with a Dual TPU card, you can leverage the APEX_0 and APEX_1 devices to distribute the workload effectively. This setup can significantly boost performance and efficiency in your machine learning tasks.
Feel free to explore the provided resources and let us know if you have any further questions! 🚀
FearL0rd
@glenn-jocher where is the doc talking about segmentation using APEX_0 and APEX_1
Glenn JocherUltralyticsHi @FearL0rd,
For documentation on segmentation using APEX_0 and APEX_1, you can refer to the guide on exporting YOLOv8 models to TFLite Edge TPU format. This guide covers optimizing your models for high-speed, low-power inferencing on devices like the Coral Edge TPU.
To utilize both APEX_0 and APEX_1 devices, you can distribute the workload effectively across the dual TPU setup, enhancing performance and efficiency. For more detailed instructions, please visit the relevant sections in our documentation.
Feel free to reach out if you have any more questions! 😊