Click here to Skip to main content
14,979,362 members
Articles / Artificial Intelligence / Tensorflow
Posted 29 Jan 2021


2 bookmarked

Converting YOLOv5 PyTorch Model Weights to TensorFlow Lite Format

Rate me:
Please Sign up or sign in to vote.
5.00/5 (2 votes)
29 Jan 2021CPOL4 min read
In this article we test a face mask detector on a regular computer.
Here we make our model understandable to TensorFlow Lite, the lightweight version of TensorFlow specially developed to run on small devices.


In the previous article of this series, we trained and tested our YOLOv5 model for face mask detection. In this one, we’ll convert our model to TensorFlow Lite format.

I previously mentioned that we’ll be using some scripts that are still not available in the official Ultralytics repo (clone this) to make our life easier. To perform the transformation, we’ll use the script, which simplifies the PyTorch to TFLite conversion. Otherwise, we’d need to stick to the Ultralytics-suggested method that involves converting PyTorch to ONNX to TensorFlow to TFLite. Note that the last operation can fail, which is really frustrating.

To perform the conversion, run this:

import tensorflow as tf
!PYTHONPATH=. python3 /content/yolov5/models/ --weight
/content/yolov5/runs/train/exp2/weights/ --cfg models/yolov5s.yaml --img 416 --source /content/FaceMaskDataset/images/train

When passing the weights’ file path (the configuration.yaml file), indicate the image dimensions the model accepts and the source of the training dataset (the last parameter is optional). The script will use TensorFlow 2.3.1 to transform the .pt weights to the TensorFlow format and the output will be saved at /content/yolov5/runs/train/exp/weights.

Ultralytics-Suggested Method for Weights Conversion

From my perspective, this step is a bit cumbersome, but it’s necessary to show how it works. Instead of running the previous commands, run these lines:

# Uncomment all this if you want to follow the long path
#!pip install onnx>=1.7.0 # for ONNX export
#!pip install coremltools==4.0 # for CoreML export
#!python models/ --weights /content/yolov5/runs/train/exp2/weights/ --img 416 --batch 1 # export at 640x640 with batch size 1
#!pip install tensorflow-addons
#!pip install onnx-tf
#!pip install tensorflow==2.3.0
#import tensorflow_addons as tfa
#import onnx
#from onnx_tf.backend import prepare
#import tensorflow as tf
#base_model = onnx.load('/content/yolov5/runs/train/exp2/weights/best.onnx')
#to_tf = prepare(base_model)
#converter = tf.compat.v1.lite.TFLiteConverter.from_saved_model('/content/yolov5/runs/train/exp2/weights/customyolov5')
#tflite_model = converter.convert() #just FYI: this step could go wrong and your notebook instance could crash.

Testing TFLite Weights on Google Colab

Now it’s time to check if the weights conversion went well. Before doing so, we need to slightly modify the script and set the proper class names. Open up the file (/content/yolov5/, look for names = [...] on line 157 and change it to names = ['Face mask','No face mask']. Save and close the file.

If everything went well, you should be able to load and test what you've obtained. Run the lines below. They will load the YOLOv5 model with the .tflite weights and run detection on the images stored at /test_images.

!python --weight /content/yolov5/runs/train/exp2/weights/best-fp16.tflite --img 416 --source ../test_images

If all goes well, the result will be similar to this:

Image 1

And with that, you're done — at least in this Notebook! As a last step, download the weights file stored at /content/yolov5/runs/train/exp/weights/best-fp16.tflite and to use them in the real-world implementation.

TFLite Interpreter for Good Performance on Edge Devices

The YOLOv5’s script uses a regular TensorFlow library to interpret TensorFlow models, including the TFLite formatted ones. In our scenario, TensorFlow is too heavy and resource-demanding to be run on small devices. If you want to maintain good performance of detections, better stick to TFLite and its interpreter. I’ve essentially replaced all TensorFlow-related operations with their TFLite equivalents. In addition, I made some small changes to make the detector able to run on TPU/GPU: I copied the file, modified it, and saved it as You can find the file here. I invite you to compare these files to fully understand the modifications.

Testing the YOLOv5 Model Weights Locally

This step is optional but recommended. In this short test, I’ll show you how to feed your computer’s webcam output to the detector before the final deployment on Pi. I’ll also show you how to test the model with and without the TFLite interpreter. Once you’ve got the modified file, create a folder on your local computer with the name Face Mask Detection.

Get the latest PyTorch version and its dependencies by running pip3 install torch torchvision from any CLI window.

Launch a Jupyter Notebook from the directory you’ve created: open the CLI, navigate to that folder, and issue the jupyter notebook command. Once the notebook pops up, run the following cells:

#Install the appropriate tensorflow version
!pip install tensorflow==2.3.1
import torch #It's required by YOLO
import tensorflow as tf
!git clone #comment this if this is not your first run
%cd yolov5
!git checkout tf-android
#Install all dependencies indicated at requirements.txt file
#Prompt if any GPU is available
!pip install -r requirements.txt
print('All set. Using PyTorch version %s with %s' % (torch.__version__, torch.cuda.get_device_properties(0) if torch.cuda.is_available() else 'CPU'))

Before continuing, remember to modify names list at line 157 in the file and copy all the downloaded weights into the /weights folder within the YOLOv5 folder.

To feed your YOLOv5 model with the computer’s webcam, run this command in a new notebook cell:

!python --weights weights/ --img 416 --conf 0.4 --source 0 --classes 0 1

It will initiate the webcam in a separate window, identify your face, and detect if you’re wearing a face mask or not. This is what you should expect:Image 2

Image 3

If you want to test the model with its TFLite weights, you first need to install the corresponding interpreter on your machine.

If you’re using linux x86_64:


If you’re using any other OS, I would suggest you check the best version for you.

Now you can run the next cell and expect exactly the same result as before:

!python --weights weights/best-fp16.tflite --img 416 --conf 0.45 --source 0 --classes 0 1

Next Step

We’ve trained and tested the YOLOv5 face mask detector. In the next article, we’ll deploy it on Raspberry Pi as promised. Stay tuned!


This article, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)


About the Author

Sergio Virahonda
United States United States
Sergio Virahonda grew up in Venezuela where obtained a bachelor's degree in Telecommunications Engineering. He moved abroad 4 years ago and since then has been focused on building meaningful data science career. He's currently living in Argentina writing code as a freelance developer.

Comments and Discussions

QuestionDeploying on android Pin
ARCHANA KUMAR 202117-May-21 20:21
MemberARCHANA KUMAR 202117-May-21 20:21 
Questionerror Pin
Moeed 202127-Apr-21 2:06
MemberMoeed 202127-Apr-21 2:06 
Questionwhy does detecting image need long time when using converted tflite16 model? Pin
simiao lai10-Mar-21 19:42
Membersimiao lai10-Mar-21 19:42 
QuestionI am still getting an error with after converting it to tflite FP 16 and FP 32 both Pin
tanisha banik14-Feb-21 6:07
Membertanisha banik14-Feb-21 6:07 
QuestionCan't find in the given path Pin
tanisha banik14-Feb-21 4:21
Membertanisha banik14-Feb-21 4:21 
QuestionMessage Closed Pin
29-Jan-21 17:56
Membercambridge academy29-Jan-21 17:56 

General General    News News    Suggestion Suggestion    Question Question    Bug Bug    Answer Answer    Joke Joke    Praise Praise    Rant Rant    Admin Admin   

Use Ctrl+Left/Right to switch messages, Ctrl+Up/Down to switch threads, Ctrl+Shift+Left/Right to switch pages.