YOLOv3 in PyTorch > ONNX > CoreML > TFLite

YOLOv3

YOLOv3 🚀 is a family of object detection architectures and models pretrained on the COCO dataset, and represents Ultralytics open-source research into future vision AI methods, incorporating lessons learned and best practices evolved over thousands of hours of research and development.

Documentation

See the YOLOv3 Docs for full documentation on training, testing and deployment.

Quick Start Examples

Install

Python>=3.6.0 is required with all requirements.txt installed including PyTorch>=1.7:

$ git clone https://github.com/ultralytics/yolov3
$ cd yolov3
$ pip install -r requirements.txt

Inference

Inference with YOLOv3 and PyTorch Hub. Models automatically download from the latest YOLOv3 release.

import torch

# Model
model = torch.hub.load('ultralytics/yolov3', 'yolov3')  # or yolov3-spp, yolov3-tiny, custom

# Images
img = 'https://ultralytics.com/images/zidane.jpg'  # or file, Path, PIL, OpenCV, numpy, list

# Inference
results = model(img)

# Results
results.print()  # or .show(), .save(), .crop(), .pandas(), etc.

Inference with detect.py

detect.py runs inference on a variety of sources, downloading models automatically from the latest YOLOv3 release and saving results to runs/detect.

$ python detect.py --source 0  # webcam
                            img.jpg  # image
                            vid.mp4  # video
                            path/  # directory
                            path/*.jpg  # glob
                            'https://youtu.be/Zgi9g1ksQHc'  # YouTube
                            'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream

TrainingTutorials

Train Custom Data 🚀 RECOMMENDED
Tips for Best Training Results ☘️ RECOMMENDED
Weights & Biases Logging 🌟 NEW
Roboflow for Datasets, Labeling, and Active Learning 🌟 NEW
Multi-GPU Training
PyTorch Hub ⭐ NEW
TorchScript, ONNX, CoreML Export 🚀
Test-Time Augmentation (TTA)
Model Ensembling
Model Pruning/Sparsity
Hyperparameter Evolution
Transfer Learning with Frozen Layers ⭐ NEW
TensorRT Deployment

Environments

Get started in seconds with our verified environments. Click each icon below for details.

Integrations

Weights and Biases	Roboflow ⭐ NEW
Automatically track and visualize all your YOLOv3 training runs in the cloud with Weights & Biases	Label and export your custom datasets directly to YOLOv3 for training with Roboflow

Why YOLOv5

YOLOv3-P5 640 Figure (click to expand)

Figure Notes (click to expand)

COCO AP val denotes mAP@0.5:0.95 metric measured on the 5000-image COCO val2017 dataset over various inference sizes from 256 to 1536.
GPU Speed measures average inference time per image on COCO val2017 dataset using a AWS p3.2xlarge V100 instance at batch-size 32.
EfficientDet data from google/automl at batch size 8.
Reproduce by python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n6.pt yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt

Pretrained Checkpoints

Model	size (pixels)	mAPval 0.5:0.95	mAPval 0.5	Speed CPU b1 (ms)	Speed V100 b1 (ms)	Speed V100 b32 (ms)	params (M)	FLOPs @640 (B)
YOLOv5n	640	28.4	46.0	45	6.3	0.6	1.9	4.5
YOLOv5s	640	37.2	56.0	98	6.4	0.9	7.2	16.5
YOLOv5m	640	45.2	63.9	224	8.2	1.7	21.2	49.0
YOLOv5l	640	48.8	67.2	430	10.1	2.7	46.5	109.1
YOLOv5x	640	50.7	68.9	766	12.1	4.8	86.7	205.7

YOLOv5n6	1280	34.0	50.7	153	8.1	2.1	3.2	4.6
YOLOv5s6	1280	44.5	63.0	385	8.2	3.6	16.8	12.6
YOLOv5m6	1280	51.0	69.0	887	11.1	6.8	35.7	50.0
YOLOv5l6	1280	53.6	71.6	1784	15.8	10.5	76.8	111.4
YOLOv5x6 + TTA	1280 1536	54.7 55.4	72.4 72.3	3136 -	26.2 -	19.4 -	140.7 -	209.8 -

Table Notes (click to expand)

All checkpoints are trained to 300 epochs with default settings and hyperparameters.
mAPval values are for single-model single-scale on COCO val2017 dataset.
Reproduce by python val.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65
Speed averaged over COCO val images using a AWS p3.2xlarge instance. NMS times (~1 ms/img) not included.
Reproduce by python val.py --data coco.yaml --img 640 --conf 0.25 --iou 0.45
TTA Test Time Augmentation includes reflection and scale augmentations.
Reproduce by python val.py --data coco.yaml --img 1536 --iou 0.7 --augment

Download Details:

Author: ultralytics
Source Code: https://github.com/ultralytics/yolov3
License: GPL-3.0 license

#machinelearning #deeplearning #ios

What is GEEK

Buddha Community

YOLOv3 in PyTorch > ONNX > CoreML > TFLite

Christine Brush

1585638769

How to Build an Object Tracker Using YOLOv3, Deep SORT and TensorFlow

Object Tracking using YOLOv3, Deep Sort and Tensorflow

Learn how to build an Object Tracker using YOLOv3, Deep SORT, and Tensorflow! Run the real-time object tracker on both webcam and video. This guide will show you how to get the necessary code, setup required dependencies and run the tracker.

This repository implements YOLOv3 and Deep SORT in order to perfrom real-time object tracking. Yolov3 is an algorithm that uses deep convolutional neural networks to perform object detection. We can feed these object detections into Deep SORT (Simple Online and Realtime Tracking with a Deep Association Metric) in order for a real-time object tracker to be created.

Demo of Object Tracker

Getting started

Conda (Recommended)

# Tensorflow CPU
conda env create -f conda-cpu.yml
conda activate tracker-cpu

# Tensorflow GPU
conda env create -f conda-gpu.yml
conda activate tracker-gpu

Pip

# TensorFlow CPU
pip install -r requirements.txt

# TensorFlow GPU
pip install -r requirements-gpu.txt

Nvidia Driver (For GPU, if you haven't set it up already)

# Ubuntu 18.04
sudo add-apt-repository ppa:graphics-drivers/ppa
sudo apt install nvidia-driver-430
# Windows/Other
https://www.nvidia.com/Download/index.aspx

Downloading official pretrained weights

For Linux: Let's download official yolov3 weights pretrained on COCO dataset.

# yolov3
wget https://pjreddie.com/media/files/yolov3.weights -O weights/yolov3.weights

# yolov3-tiny
wget https://pjreddie.com/media/files/yolov3-tiny.weights -O weights/yolov3-tiny.weights

For Windows: You can download the yolov3 weights by clicking here and yolov3-tiny here then save them to the weights folder.

Using Custom trained weights

Learn How To Train Custom YOLOV3 Weights Here: https://www.youtube.com/watch?v=zJDUhGL26iU

Add your custom weights file to weights folder and your custom .names file into data/labels folder.

Saving your yolov3 weights as a TensorFlow model.

Load the weights using load_weights.py script. This will convert the yolov3 weights into TensorFlow .tf model files!

# yolov3
python load_weights.py

# yolov3-tiny
python load_weights.py --weights ./weights/yolov3-tiny.weights --output ./weights/yolov3-tiny.tf --tiny

# yolov3-custom (add --tiny flag if your custom weights were trained for tiny model)
python load_weights.py --weights ./weights/<YOUR CUSTOM WEIGHTS FILE> --output ./weights/yolov3-custom.tf --num_classes <# CLASSES>

After executing one of the above lines, you should see proper .tf files in your weights folder. You are now ready to run object tracker.

Running the Object Tracker

Now you can run the object tracker for whichever model you have created, pretrained, tiny, or custom.

# yolov3 on video
python object_tracker.py --video ./data/video/test.mp4 --output ./data/video/results.avi

#yolov3 on webcam 
python object_tracker.py --video 0 --output ./data/video/results.avi

#yolov3-tiny 
python object_tracker.py --video ./data/video/test.mp4 --output ./data/video/results.avi --weights ./weights/yolov3-tiny.tf --tiny

#yolov3-custom (add --tiny flag if your custom weights were trained for tiny model)
python object_tracker.py --video ./data/video/test.mp4 --output ./data/video/results.avi --weights ./weights/yolov3-custom.tf --num_classes <# CLASSES> --classes ./data/labels/<YOUR CUSTOM .names FILE>

The output flag saves your object tracker results as an avi file for you to watch back. It is not necessary to have the flag if you don't want to save the resulting video.

There is a test video uploaded in the data/video folder called test.mp4. If you followed all the steps properly with the pretrained coco yolov3.weights model then when your run the object tracker wiht the first command above you should see the following.

Video Example

Demo of Object Tracker

Webcam Example

This is a demo of running the object tracker using the above command for running the object tracker on your webcam. Webcam Demo

Command Line Args Reference

load_weights.py:
  --output: path to output
    (default: './weights/yolov3.tf')
  --[no]tiny: yolov3 or yolov3-tiny
    (default: 'false')
  --weights: path to weights file
    (default: './weights/yolov3.weights')
  --num_classes: number of classes in the model
    (default: '80')
    (an integer)
    
object_tracker.py:
  --classes: path to classes file
    (default: './data/labels/coco.names')
  --video: path to input video (use 0 for webcam)
    (default: './data/video/test.mp4')
  --output: path to output video (remember to set right codec for given format. e.g. XVID for .avi)
    (default: None)
  --output_format: codec used in VideoWriter when saving video to file
    (default: 'XVID)
  --[no]tiny: yolov3 or yolov3-tiny
    (default: 'false')
  --weights: path to weights file
    (default: './weights/yolov3.tf')
  --num_classes: number of classes in the model
    (default: '80')
    (an integer)
  --yolo_max_boxes: maximum number of detections at one time
    (default: '100')
    (an integer)
  --yolo_iou_threshold: iou threshold for how close two boxes can be before they are detected as one box
    (default: 0.5)
    (a float)
  --yolo_score_threshold: score threshold for confidence level in detection for detection to count
    (default: 0.5)
    (a float)

Acknowledgments

Download Details:

Author: theAIGuysCode
Download Link: Download The Source Code
Official Website: https://github.com/theAIGuysCode/yolov3_deepsort
License: GPL-3.0 license

Subscribe: https://www.youtube.com/c/TheAIGuy/featured

#tensorflow #yolov3 #python

Alec Nikolaus

1602954000

My Journey in Converting PyTorch to TensorFlow Lite

Intro

I recently had to convert a deep learning model (a MobileNetV2 variant) from PyTorch to TensorFlow Lite. It was a long, complicated journey, involved jumping through a lot of hoops to make it work. I found myself collecting pieces of information from Stackoverflow posts and GitHub issues. My goal is to share my experience in an attempt to help someone else who is lost like I was.

DISCLAIMER: This is not a guide_ on how to properly do this conversion. I only wish to share my experience. I might have done it wrong (especially because I have no experience with Tensorflow). If you notice something that I could have done better/differently — please comment and I’ll update the post accordingly._

The Mission

Convert a deep learning model (a MobileNetV2 variant) from Pytorch to TensorFlow Lite. The conversion process should be:

Pytorch →ONNX → Tensorflow → TFLite

Tests

In order to test the converted models, a set of roughly 1,000 input tensors was generated, and the PyTorch model’s output was calculated for each. That set was later used to test each of the converted models, by comparing their yielded outputs against the original outputs, via a mean error metric, over the entire set. The mean error reflects how different are the converted model outputs compared to the original PyTorch model outputs, over the same input.

I decided to treat a model with a mean error smaller than 1e-6 as a successfully converted model.

It might also be important to note that I added the batch dimension in the tensor, even though it was 1. I had no reason doing so other than a hunch that comes from my previous experience converting PyTorch to DLC models.

#mlops #tensorflow #onnx #pytorch #tflite

Michio JP

1651733745

Build an Object Tracker using YOLOv3, Deep SORT and Tensorflow

Object Tracking using YOLOv3, Deep Sort and Tensorflow

This repository implements YOLOv3 and Deep SORT in order to perfrom real-time object tracking. Yolov3 is an algorithm that uses deep convolutional neural networks to perform object detection. We can feed these object detections into Deep SORT (Simple Online and Realtime Tracking with a Deep Association Metric) in order for a real-time object tracker to be created.

Getting started

Conda (Recommended)

# Tensorflow CPU
conda env create -f conda-cpu.yml
conda activate tracker-cpu

# Tensorflow GPU
conda env create -f conda-gpu.yml
conda activate tracker-gpu

Pip

# TensorFlow CPU
pip install -r requirements.txt

# TensorFlow GPU
pip install -r requirements-gpu.txt

Nvidia Driver (For GPU, if you haven't set it up already)

# Ubuntu 18.04
sudo add-apt-repository ppa:graphics-drivers/ppa
sudo apt install nvidia-driver-430
# Windows/Other
https://www.nvidia.com/Download/index.aspx

Downloading official pretrained weights

For Linux: Let's download official yolov3 weights pretrained on COCO dataset.

# yolov3
wget https://pjreddie.com/media/files/yolov3.weights -O weights/yolov3.weights

# yolov3-tiny
wget https://pjreddie.com/media/files/yolov3-tiny.weights -O weights/yolov3-tiny.weights

For Windows: You can download the yolov3 weights by clicking here and yolov3-tiny here then save them to the weights folder.

Using Custom trained weights

Learn How To Train Custom YOLOV3 Weights Here: https://www.youtube.com/watch?v=zJDUhGL26iU

Add your custom weights file to weights folder and your custom .names file into data/labels folder.

Saving your yolov3 weights as a TensorFlow model.

Load the weights using load_weights.py script. This will convert the yolov3 weights into TensorFlow .tf model files!

# yolov3
python load_weights.py

# yolov3-tiny
python load_weights.py --weights ./weights/yolov3-tiny.weights --output ./weights/yolov3-tiny.tf --tiny

# yolov3-custom (add --tiny flag if your custom weights were trained for tiny model)
python load_weights.py --weights ./weights/<YOUR CUSTOM WEIGHTS FILE> --output ./weights/yolov3-custom.tf --num_classes <# CLASSES>

After executing one of the above lines, you should see proper .tf files in your weights folder. You are now ready to run object tracker.

Running the Object Tracker

Now you can run the object tracker for whichever model you have created, pretrained, tiny, or custom.

# yolov3 on video
python object_tracker.py --video ./data/video/test.mp4 --output ./data/video/results.avi

#yolov3 on webcam 
python object_tracker.py --video 0 --output ./data/video/results.avi

#yolov3-tiny 
python object_tracker.py --video ./data/video/test.mp4 --output ./data/video/results.avi --weights ./weights/yolov3-tiny.tf --tiny

#yolov3-custom (add --tiny flag if your custom weights were trained for tiny model)
python object_tracker.py --video ./data/video/test.mp4 --output ./data/video/results.avi --weights ./weights/yolov3-custom.tf --num_classes <# CLASSES> --classes ./data/labels/<YOUR CUSTOM .names FILE>

The output flag saves your object tracker results as an avi file for you to watch back. It is not necessary to have the flag if you don't want to save the resulting video.

There is a test video uploaded in the data/video folder called test.mp4. If you followed all the steps properly with the pretrained coco yolov3.weights model then when your run the object tracker wiht the first command above you should see the following.

Video Example

Webcam Example

This is a demo of running the object tracker using the above command for running the object tracker on your webcam.

Command Line Args Reference

load_weights.py:
  --output: path to output
    (default: './weights/yolov3.tf')
  --[no]tiny: yolov3 or yolov3-tiny
    (default: 'false')
  --weights: path to weights file
    (default: './weights/yolov3.weights')
  --num_classes: number of classes in the model
    (default: '80')
    (an integer)
    
object_tracker.py:
  --classes: path to classes file
    (default: './data/labels/coco.names')
  --video: path to input video (use 0 for webcam)
    (default: './data/video/test.mp4')
  --output: path to output video (remember to set right codec for given format. e.g. XVID for .avi)
    (default: None)
  --output_format: codec used in VideoWriter when saving video to file
    (default: 'XVID)
  --[no]tiny: yolov3 or yolov3-tiny
    (default: 'false')
  --weights: path to weights file
    (default: './weights/yolov3.tf')
  --num_classes: number of classes in the model
    (default: '80')
    (an integer)
  --yolo_max_boxes: maximum number of detections at one time
    (default: '100')
    (an integer)
  --yolo_iou_threshold: iou threshold for how close two boxes can be before they are detected as one box
    (default: 0.5)
    (a float)
  --yolo_score_threshold: score threshold for confidence level in detection for detection to count
    (default: 0.5)
    (a float)

Acknowledgments

Download Details:

Author: theAIGuysCode
Download Link: Download The Source Code
Official Website: https://github.com/theAIGuysCode/yolov3_deepsort
License: GPL-3.0 License

#python #yolo

Matt Cruickshank

1616510100

ONNX: Preventing Framework Lock in

In this blog, we are going to see what the ONNX standard is, its components and how to carry out interoperability between different Deep Learning frameworks. This blog will address the following sections:

Introduction
What is ONNX?
What is ONNX Runtime?
Interoperability: from PyTorch to other Frameworks

So let’s get started!

#onnx #tensorflow #interoperability #pytorch #onnx-runtime

Alexander Tyler

1651649644

YOLOv5 🚀 in PyTorch, ONNX, CoreML, TFLite

YOLOv5 🚀 is a family of object detection architectures and models pretrained on the COCO dataset, and represents Ultralytics open-source research into future vision AI methods, incorporating lessons learned and best practices evolved over thousands of hours of research and development.

Documentation

See the YOLOv5 Docs for full documentation on training, testing and deployment.

Quick Start Examples

Install

Clone repo and install requirements.txt in a Python>=3.7.0 environment, including PyTorch>=1.7.

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

Inference

YOLOv5 PyTorch Hub inference. Models download automatically from the latest YOLOv5 release.

import torch

# Model
model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # or yolov5n - yolov5x6, custom

# Images
img = 'https://ultralytics.com/images/zidane.jpg'  # or file, Path, PIL, OpenCV, numpy, list

# Inference
results = model(img)

# Results
results.print()  # or .show(), .save(), .crop(), .pandas(), etc.

Inference with detect.py

detect.py runs inference on a variety of sources, downloading models automatically from the latest YOLOv5 release and saving results to runs/detect.

python detect.py --source 0  # webcam
                          img.jpg  # image
                          vid.mp4  # video
                          path/  # directory
                          path/*.jpg  # glob
                          'https://youtu.be/Zgi9g1ksQHc'  # YouTube
                          'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream

Training

The commands below reproduce YOLOv5 COCO results. Models and datasets download automatically from the latest YOLOv5 release. Training times for YOLOv5n/s/m/l/x are 1/2/4/6/8 days on a V100 GPU (Multi-GPU times faster). Use the largest --batch-size possible, or pass --batch-size -1 for YOLOv5 AutoBatch. Batch sizes shown for V100-16GB.

python train.py --data coco.yaml --cfg yolov5n.yaml --weights '' --batch-size 128
                                       yolov5s                                64
                                       yolov5m                                40
                                       yolov5l                                24
                                       yolov5x                                16

Tutorials

Train Custom Data 🚀 RECOMMENDED
Tips for Best Training Results ☘️ RECOMMENDED
Weights & Biases Logging 🌟 NEW
Roboflow for Datasets, Labeling, and Active Learning 🌟 NEW
Multi-GPU Training
PyTorch Hub ⭐ NEW
TFLite, ONNX, CoreML, TensorRT Export 🚀
Test-Time Augmentation (TTA)
Model Ensembling
Model Pruning/Sparsity
Hyperparameter Evolution
Transfer Learning with Frozen Layers ⭐ NEW
Architecture Summary ⭐ NEW

Integrations

Weights and Biases	Roboflow ⭐ NEW
Automatically track and visualize all your YOLOv5 training runs in the cloud with Weights & Biases	Label and export your custom datasets directly to YOLOv5 for training with Roboflow

Why YOLOv5

YOLOv5-P5 640 Figure (click to expand)

Figure Notes (click to expand)

COCO AP val denotes mAP@0.5:0.95 metric measured on the 5000-image COCO val2017 dataset over various inference sizes from 256 to 1536.
GPU Speed measures average inference time per image on COCO val2017 dataset using a AWS p3.2xlarge V100 instance at batch-size 32.
EfficientDet data from google/automl at batch size 8.
Reproduce by python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n6.pt yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt

Pretrained Checkpoints

Model	size (pixels)	mAPval 0.5:0.95	mAPval 0.5	Speed CPU b1 (ms)	Speed V100 b1 (ms)	Speed V100 b32 (ms)	params (M)	FLOPs @640 (B)
[YOLOv5n][assets]	640	28.0	45.7	45	6.3	0.6	1.9	4.5
[YOLOv5s][assets]	640	37.4	56.8	98	6.4	0.9	7.2	16.5
[YOLOv5m][assets]	640	45.4	64.1	224	8.2	1.7	21.2	49.0
[YOLOv5l][assets]	640	49.0	67.3	430	10.1	2.7	46.5	109.1
[YOLOv5x][assets]	640	50.7	68.9	766	12.1	4.8	86.7	205.7

[YOLOv5n6][assets]	1280	36.0	54.4	153	8.1	2.1	3.2	4.6
[YOLOv5s6][assets]	1280	44.8	63.7	385	8.2	3.6	12.6	16.8
[YOLOv5m6][assets]	1280	51.3	69.3	887	11.1	6.8	35.7	50.0
[YOLOv5l6][assets]	1280	53.7	71.3	1784	15.8	10.5	76.8	111.4
[YOLOv5x6][assets] + [TTA][TTA]	1280 1536	55.0 55.8	72.7 72.7	3136 -	26.2 -	19.4 -	140.7 -	209.8 -

Table Notes (click to expand)

All checkpoints are trained to 300 epochs with default settings. Nano and Small models use hyp.scratch-low.yaml hyps, all others use hyp.scratch-high.yaml.
mAPval values are for single-model single-scale on COCO val2017 dataset.
Reproduce by python val.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65
Speed averaged over COCO val images using a AWS p3.2xlarge instance. NMS times (~1 ms/img) not included.
Reproduce by python val.py --data coco.yaml --img 640 --task speed --batch 1
TTA Test Time Augmentation includes reflection and scale augmentations.
Reproduce by python val.py --data coco.yaml --img 1536 --iou 0.7 --augment

Contact

For YOLOv5 bugs and feature requests please visit GitHub Issues. For business inquiries or professional support requests please visit https://ultralytics.com/contact.

Download Details:
Author: ultralytics
Source Code: https://github.com/ultralytics/yolov5
License: GPL-3.0 License
#yolo #pytorch