Get Started

Export YOLO26 Models to Google Coral Edge TPU (TFLite) Format

Deploying computer vision models on devices with limited computational power, such as mobile or embedded systems, can be tricky. Using a model format that is optimized for faster performance simplifies the process. The TensorFlow Lite Edge TPU model format is designed to use minimal power while delivering fast performance for neural networks.

Exporting to the Edge TPU format lets you optimize your Ultralytics YOLO26 models for high-speed, low-power inference. In this guide, we'll walk you through converting your models to the Edge TPU format, making it easier for your models to perform well on various mobile and embedded devices.

Why Should You Export to Edge TPU?#

Exporting models to TensorFlow Edge TPU makes machine learning tasks fast and efficient. This technology suits applications with limited power, computing resources, and connectivity. The Edge TPU is Google's edge version of its Tensor Processing Unit (TPU) hardware accelerator. It speeds up TensorFlow Lite models on edge devices. The image below shows an example of the process involved.

TensorFlow Lite Edge TPU compilation workflow

The Edge TPU works with quantized models. Quantization makes models smaller and faster without losing much accuracy. It is ideal for the limited resources of edge computing, allowing applications to respond quickly by reducing latency and allowing for quick data processing locally, without cloud dependency. Local processing also keeps user data private and secure since it's not sent to a remote server.

Key Features of Edge TPU#

Here are the key features that make Edge TPU a strong model format choice for developers:

  • Optimized Performance on Edge Devices: The Edge TPU delivers fast neural network inference through quantization, model optimization, hardware acceleration, and compiler optimization. Its minimalistic architecture contributes to its smaller size and cost-efficiency.

  • High Computational Throughput: Edge TPU combines specialized hardware acceleration and efficient runtime execution to achieve high computational throughput. It is well-suited for deploying machine learning models with stringent performance requirements on edge devices.

  • Efficient Matrix Computations: The TensorFlow Edge TPU is optimized for matrix operations, which are crucial for neural network computations. This efficiency is key in machine learning models, particularly those requiring numerous and complex matrix multiplications and transformations.

Deployment Options with Edge TPU#

Before exporting YOLO26 models to the Edge TPU format, it helps to understand where these models are typically used.

Edge TPU offers various deployment options for machine learning models, including:

  • On-Device Deployment: TensorFlow Edge TPU models can be directly deployed on mobile and embedded devices. On-device deployment allows the models to execute directly on the hardware, eliminating the need for cloud connectivity, either by embedding the model in the application bundle or downloading it on demand.

  • Hybrid Deployment: A hybrid approach combines on-device and cloud deployment and offers a versatile and scalable solution for deploying machine learning models. Advantages include on-device processing for quick responses and cloud computing for more complex computations.

Supported Tasks#

Edge TPU export supports six of the seven Ultralytics tasks. Semantic segmentation is available only with YOLO26, the only family that ships that head. Depth estimation is not supported because its INT8 model emits an EXP v2 operator that the Edge TPU compiler cannot parse.

TaskYOLOv8YOLO11YOLO26
Detectāœ…āœ…āœ…
Segmentāœ…āœ…āœ…
SemanticāŒāŒāœ…
DepthāŒāŒāŒ
Classifyāœ…āœ…āœ…
Poseāœ…āœ…āœ…
OBBāœ…āœ…āœ…

The Edge TPU compiler maps the operations it supports onto the accelerator and leaves the rest on the CPU, so task support does not mean every operation runs on the TPU.

Exporting YOLO26 Models to Edge TPU#

You can expand model compatibility and deployment flexibility by converting YOLO26 models to TensorFlow Edge TPU.

Installation#

To install the required package, run:

Installation
# Install the required package for YOLO26
pip install ultralytics

For detailed instructions and best practices related to the installation process, check our Ultralytics Installation guide. While installing the required packages for YOLO26, if you encounter any difficulties, consult our Common Issues guide for solutions and tips.

Usage#

All Ultralytics YOLO26 models are designed to support export out of the box, making it easy to integrate them into your preferred deployment workflow. You can view the full list of supported export formats and configuration options to choose the best setup for your application.

The Edge TPU format supports the Export, Predict, and Validate modes. Inference and validation run on Coral Edge TPU hardware. Export your model, then load the exported model to run inference or validate its accuracy.

Export
from ultralytics import YOLO

# Load a YOLO26 model
model = YOLO("yolo26n.pt")

# Export the model to Edge TPU format
model.export(format="edgetpu")  # creates 'yolo26n_saved_model/yolo26n_full_integer_quant_edgetpu.tflite'
Predict
from ultralytics import YOLO

# Load the exported Edge TPU model
model = YOLO("yolo26n_saved_model/yolo26n_full_integer_quant_edgetpu.tflite")

# Run inference
results = model("https://ultralytics.com/images/bus.jpg")
Validate
from ultralytics import YOLO

# Load the exported Edge TPU model
model = YOLO("yolo26n_saved_model/yolo26n_full_integer_quant_edgetpu.tflite")

# Validate accuracy on the COCO8 dataset
metrics = model.val(data="coco8.yaml")

Export Arguments#

ArgumentTypeDefaultDescription
formatstr'edgetpu'Target format for the exported model, defining compatibility with various deployment environments.
imgszint or tuple640Desired image size for the model input. Can be an integer for square images or a tuple (height, width) for specific dimensions.
quantizeint or str8/autoQuantization precision. 8 (INT8) is required and auto-enabled for Edge TPU, compressing the model and speeding up inference with minimal accuracy loss on edge devices. Replaces the deprecated half/int8 flags.
opsetintNoneSpecifies the ONNX opset version for the intermediate ONNX graph. If not set, uses opset 18 (lower on PyTorch < 2.4), capped at the installed onnx version.
datastrNonePath to the dataset YAML, essential for quantization; classification instead takes a dataset directory or a built-in dataset name. If omitted with quantize=8, Ultralytics selects the default calibration dataset for the model task.
fractionfloat, int, or list1.0Calibration subset as a ratio, image count, or [train, val, test] ratios/counts. Two-item lists leave test full, while 0 skips it.
devicestrNoneSpecifies the device for exporting: CPU (device=cpu).
Tip

Use an x86 Linux machine when exporting to Edge TPU.

For more details about the export process, visit the Ultralytics documentation page on exporting.

Deploying Exported YOLO26 Edge TPU Models#

After successfully exporting your Ultralytics YOLO26 models to Edge TPU format, you can now deploy them. The primary and recommended first step for running a Edge TPU model is to use the YOLO("model_edgetpu.tflite") method, as outlined in the previous usage code snippet.

However, for in-depth instructions on deploying your Edge TPU models, take a look at the following resources:

Summary#

In this guide, we've learned how to export Ultralytics YOLO26 models to Edge TPU format. By following the steps above, you can run your computer vision applications faster and with less power on edge devices.

For further details on usage, visit the Coral Edge TPU official website.

FAQ#

  • To export a YOLO26 model to Edge TPU format, you can follow these steps:

    Usage
    from ultralytics import YOLO
    
    # Load a YOLO26 model
    model = YOLO("yolo26n.pt")
    
    # Export the model to Edge TPU format
    model.export(format="edgetpu")  # creates 'yolo26n_saved_model/yolo26n_full_integer_quant_edgetpu.tflite'
    
    # Load the exported Edge TPU model
    edgetpu_model = YOLO("yolo26n_saved_model/yolo26n_full_integer_quant_edgetpu.tflite")
    
    # Run inference
    results = edgetpu_model("https://ultralytics.com/images/bus.jpg")

    For complete details on exporting models to other formats, refer to our export guide.

  • Exporting YOLO26 models to Edge TPU offers several benefits:

    • Optimized Performance: Achieve high-speed neural network performance with minimal power consumption.
    • Reduced Latency: Quick local data processing without the need for cloud dependency.
    • Enhanced Privacy: Local processing keeps user data private and secure.

    This makes it ideal for applications in edge computing, where devices have limited power and computational resources.

  • Yes, TensorFlow Lite Edge TPU models can be deployed directly on mobile and embedded devices. This deployment approach allows models to execute directly on the hardware, offering faster and more efficient inferencing. For integration examples, check our guide on deploying Coral Edge TPU on Raspberry Pi.

  • Common use cases for Edge TPU models include:

    • Smart Cameras: Enhancing real-time image and video analysis.
    • IoT Devices: Enabling smart home and industrial automation.
    • Healthcare: Accelerating medical imaging and diagnostics.
    • Retail: Improving inventory management and customer behavior analysis.

    These applications benefit from the high performance and low power consumption of Edge TPU models. Discover more about usage scenarios.

  • If you encounter issues while exporting or deploying Edge TPU models, refer to our Common Issues guide for troubleshooting tips. This guide covers common problems and solutions to help you ensure smooth operation. For additional support, visit our Help Center.

Comments30

Ask a question, share your results, or help someone else.

  1. faizaanscnzGitHub

    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)

  2. walissongGitHub

    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.

  3. dbroGitHub

    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 āœ… 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 āœ… 0.0s, saved as 'yolo11n_saved_model/yolo11n_full_integer_quant_edgetpu.tflite' (0.0 MB) ...

  4. manu13008GitHub

    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 :)

    1. 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.

  5. Abdullah-OryGitHub

    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 šŸš€ 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 āœ… 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 āœ… 248.1s, saved as '/content/yolo11n_saved_model' (36.1 MB) Edge TPU: WARNING āš ļø 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 āœ… 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

    1. 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.

  6. MECHAAMERGitHub

    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,

    1. 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.

    2. MECHAAMERGitHub

      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?

    3. MECHAAMERGitHub

      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?

    4. Glenn JocherUltralytics

      For 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.

    5. MECHAAMERGitHub

      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.tflite

      I 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

    6. Glenn JocherUltralytics

      It 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.

    7. MECHAAMERGitHub

      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).

    8. 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.

  7. Taufiq-AhmedGitHub

    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.

    1. 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!

  8. samphonicGitHub

    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?

    1. 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 edgetpu interpreter 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.

    1. 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! šŸš€

    2. Glenn JocherUltralytics

      Hi @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! 😊