Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices

Overview

Intro

Build Status codecov

Real-time object detection and classification. Paper: version 1, version 2.

Read more about YOLO (in darknet) and download weight files here. In case the weight file cannot be found, I uploaded some of mine here, which include yolo-full and yolo-tiny of v1.0, tiny-yolo-v1.1 of v1.1 and yolo, tiny-yolo-voc of v2.

See demo below or see on this imgur

Dependencies

Python3, tensorflow 1.0, numpy, opencv 3.

Citation

@article{trieu2018darkflow,
  title={Darkflow},
  author={Trieu, Trinh Hoang},
  journal={GitHub Repository. Available online: https://github. com/thtrieu/darkflow (accessed on 14 February 2019)},
  year={2018}
}

Getting started

You can choose one of the following three ways to get started with darkflow.

  1. Just build the Cython extensions in place. NOTE: If installing this way you will have to use ./flow in the cloned darkflow directory instead of flow as darkflow is not installed globally.

    python3 setup.py build_ext --inplace
    
  2. Let pip install darkflow globally in dev mode (still globally accessible, but changes to the code immediately take effect)

    pip install -e .
    
  3. Install with pip globally

    pip install .
    

Update

Android demo on Tensorflow's here

I am looking for help:

  • help wanted labels in issue track

Parsing the annotations

Skip this if you are not training or fine-tuning anything (you simply want to forward flow a trained net)

For example, if you want to work with only 3 classes tvmonitor, person, pottedplant; edit labels.txt as follows

tvmonitor
person
pottedplant

And that's it. darkflow will take care of the rest. You can also set darkflow to load from a custom labels file with the --labels flag (i.e. --labels myOtherLabelsFile.txt). This can be helpful when working with multiple models with different sets of output labels. When this flag is not set, darkflow will load from labels.txt by default (unless you are using one of the recognized .cfg files designed for the COCO or VOC dataset - then the labels file will be ignored and the COCO or VOC labels will be loaded).

Design the net

Skip this if you are working with one of the original configurations since they are already there. Otherwise, see the following example:

...

[convolutional]
batch_normalize = 1
size = 3
stride = 1
pad = 1
activation = leaky

[maxpool]

[connected]
output = 4096
activation = linear

...

Flowing the graph using flow

# Have a look at its options
flow --h

First, let's take a closer look at one of a very useful option --load

# 1. Load tiny-yolo.weights
flow --model cfg/tiny-yolo.cfg --load bin/tiny-yolo.weights

# 2. To completely initialize a model, leave the --load option
flow --model cfg/yolo-new.cfg

# 3. It is useful to reuse the first identical layers of tiny for `yolo-new`
flow --model cfg/yolo-new.cfg --load bin/tiny-yolo.weights
# this will print out which layers are reused, which are initialized

All input images from default folder sample_img/ are flowed through the net and predictions are put in sample_img/out/. We can always specify more parameters for such forward passes, such as detection threshold, batch size, images folder, etc.

# Forward all images in sample_img/ using tiny yolo and 100% GPU usage
flow --imgdir sample_img/ --model cfg/tiny-yolo.cfg --load bin/tiny-yolo.weights --gpu 1.0

json output can be generated with descriptions of the pixel location of each bounding box and the pixel location. Each prediction is stored in the sample_img/out folder by default. An example json array is shown below.

# Forward all images in sample_img/ using tiny yolo and JSON output.
flow --imgdir sample_img/ --model cfg/tiny-yolo.cfg --load bin/tiny-yolo.weights --json

JSON output:

[{"label":"person", "confidence": 0.56, "topleft": {"x": 184, "y": 101}, "bottomright": {"x": 274, "y": 382}},
{"label": "dog", "confidence": 0.32, "topleft": {"x": 71, "y": 263}, "bottomright": {"x": 193, "y": 353}},
{"label": "horse", "confidence": 0.76, "topleft": {"x": 412, "y": 109}, "bottomright": {"x": 592,"y": 337}}]
  • label: self explanatory
  • confidence: somewhere between 0 and 1 (how confident yolo is about that detection)
  • topleft: pixel coordinate of top left corner of box.
  • bottomright: pixel coordinate of bottom right corner of box.

Training new model

Training is simple as you only have to add option --train. Training set and annotation will be parsed if this is the first time a new configuration is trained. To point to training set and annotations, use option --dataset and --annotation. A few examples:

# Initialize yolo-new from yolo-tiny, then train the net on 100% GPU:
flow --model cfg/yolo-new.cfg --load bin/tiny-yolo.weights --train --gpu 1.0

# Completely initialize yolo-new and train it with ADAM optimizer
flow --model cfg/yolo-new.cfg --train --trainer adam

During training, the script will occasionally save intermediate results into Tensorflow checkpoints, stored in ckpt/. To resume to any checkpoint before performing training/testing, use --load [checkpoint_num] option, if checkpoint_num < 0, darkflow will load the most recent save by parsing ckpt/checkpoint.

# Resume the most recent checkpoint for training
flow --train --model cfg/yolo-new.cfg --load -1

# Test with checkpoint at step 1500
flow --model cfg/yolo-new.cfg --load 1500

# Fine tuning yolo-tiny from the original one
flow --train --model cfg/tiny-yolo.cfg --load bin/tiny-yolo.weights

Example of training on Pascal VOC 2007:

# Download the Pascal VOC dataset:
curl -O https://pjreddie.com/media/files/VOCtest_06-Nov-2007.tar
tar xf VOCtest_06-Nov-2007.tar

# An example of the Pascal VOC annotation format:
vim VOCdevkit/VOC2007/Annotations/000001.xml

# Train the net on the Pascal dataset:
flow --model cfg/yolo-new.cfg --train --dataset "~/VOCdevkit/VOC2007/JPEGImages" --annotation "~/VOCdevkit/VOC2007/Annotations"

Training on your own dataset

The steps below assume we want to use tiny YOLO and our dataset has 3 classes

  1. Create a copy of the configuration file tiny-yolo-voc.cfg and rename it according to your preference tiny-yolo-voc-3c.cfg (It is crucial that you leave the original tiny-yolo-voc.cfg file unchanged, see below for explanation).

  2. In tiny-yolo-voc-3c.cfg, change classes in the [region] layer (the last layer) to the number of classes you are going to train for. In our case, classes are set to 3.

    ...
    
    [region]
    anchors = 1.08,1.19,  3.42,4.41,  6.63,11.38,  9.42,5.11,  16.62,10.52
    bias_match=1
    classes=3
    coords=4
    num=5
    softmax=1
    
    ...
  3. In tiny-yolo-voc-3c.cfg, change filters in the [convolutional] layer (the second to last layer) to num * (classes + 5). In our case, num is 5 and classes are 3 so 5 * (3 + 5) = 40 therefore filters are set to 40.

    ...
    
    [convolutional]
    size=1
    stride=1
    pad=1
    filters=40
    activation=linear
    
    [region]
    anchors = 1.08,1.19,  3.42,4.41,  6.63,11.38,  9.42,5.11,  16.62,10.52
    
    ...
  4. Change labels.txt to include the label(s) you want to train on (number of labels should be the same as the number of classes you set in tiny-yolo-voc-3c.cfg file). In our case, labels.txt will contain 3 labels.

    label1
    label2
    label3
    
  5. Reference the tiny-yolo-voc-3c.cfg model when you train.

    flow --model cfg/tiny-yolo-voc-3c.cfg --load bin/tiny-yolo-voc.weights --train --annotation train/Annotations --dataset train/Images

  • Why should I leave the original tiny-yolo-voc.cfg file unchanged?

    When darkflow sees you are loading tiny-yolo-voc.weights it will look for tiny-yolo-voc.cfg in your cfg/ folder and compare that configuration file to the new one you have set with --model cfg/tiny-yolo-voc-3c.cfg. In this case, every layer will have the same exact number of weights except for the last two, so it will load the weights into all layers up to the last two because they now contain different number of weights.

Camera/video file demo

For a demo that entirely runs on the CPU:

flow --model cfg/yolo-new.cfg --load bin/yolo-new.weights --demo videofile.avi

For a demo that runs 100% on the GPU:

flow --model cfg/yolo-new.cfg --load bin/yolo-new.weights --demo videofile.avi --gpu 1.0

To use your webcam/camera, simply replace videofile.avi with keyword camera.

To save a video with predicted bounding box, add --saveVideo option.

Using darkflow from another python application

Please note that return_predict(img) must take an numpy.ndarray. Your image must be loaded beforehand and passed to return_predict(img). Passing the file path won't work.

Result from return_predict(img) will be a list of dictionaries representing each detected object's values in the same format as the JSON output listed above.

from darkflow.net.build import TFNet
import cv2

options = {"model": "cfg/yolo.cfg", "load": "bin/yolo.weights", "threshold": 0.1}

tfnet = TFNet(options)

imgcv = cv2.imread("./sample_img/sample_dog.jpg")
result = tfnet.return_predict(imgcv)
print(result)

Save the built graph to a protobuf file (.pb)

## Saving the lastest checkpoint to protobuf file
flow --model cfg/yolo-new.cfg --load -1 --savepb

## Saving graph and weights to protobuf file
flow --model cfg/yolo.cfg --load bin/yolo.weights --savepb

When saving the .pb file, a .meta file will also be generated alongside it. This .meta file is a JSON dump of everything in the meta dictionary that contains information nessecary for post-processing such as anchors and labels. This way, everything you need to make predictions from the graph and do post processing is contained in those two files - no need to have the .cfg or any labels file tagging along.

The created .pb file can be used to migrate the graph to mobile devices (JAVA / C++ / Objective-C++). The name of input tensor and output tensor are respectively 'input' and 'output'. For further usage of this protobuf file, please refer to the official documentation of Tensorflow on C++ API here. To run it on, say, iOS application, simply add the file to Bundle Resources and update the path to this file inside source code.

Also, darkflow supports loading from a .pb and .meta file for generating predictions (instead of loading from a .cfg and checkpoint or .weights).

## Forward images in sample_img for predictions based on protobuf file
flow --pbLoad built_graph/yolo.pb --metaLoad built_graph/yolo.meta --imgdir sample_img/

If you'd like to load a .pb and .meta file when using return_predict() you can set the "pbLoad" and "metaLoad" options in place of the "model" and "load" options you would normally set.

That's all.

Owner
Trieu
Google Brain Resident 2017-2019. Doing research - engineering projects in Machine Learning - Deep Learning.
Trieu
ICCV2021 - A New Journey from SDRTV to HDRTV.

ICCV2021 - A New Journey from SDRTV to HDRTV.

XyChen 82 Dec 27, 2022
Symbolic Music Generation with Diffusion Models

Symbolic Music Generation with Diffusion Models Supplementary code release for our work Symbolic Music Generation with Diffusion Models. Installation

Magenta 119 Jan 07, 2023
Official implementation of Rich Semantics Improve Few-Shot Learning (BMVC, 2021)

Rich Semantics Improve Few-Shot Learning Paper Link Abstract : Human learning benefits from multi-modal inputs that often appear as rich semantics (e.

Mohamed Afham 11 Jul 26, 2022
Code for the published paper : Learning to recognize rare traffic sign

Improving traffic sign recognition by active search This repo contains code for the paper : "Learning to recognise rare traffic signs" How to use this

samsja 4 Jan 05, 2023
2D Human Pose estimation using transformers. Implementation in Pytorch

PE-former: Pose Estimation Transformer Vision transformer architectures perform very well for image classification tasks. Efforts to solve more challe

Panteleris Paschalis 23 Oct 17, 2022
Pytorch implementation of Masked Auto-Encoder

Masked Auto-Encoder (MAE) Pytorch implementation of Masked Auto-Encoder: Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, Ross Girshick

Jiyuan 22 Dec 13, 2022
Implementation for On Provable Benefits of Depth in Training Graph Convolutional Networks

Implementation for On Provable Benefits of Depth in Training Graph Convolutional Networks Setup This implementation is based on PyTorch = 1.0.0. Smal

Weilin Cong 8 Oct 28, 2022
PyTorch Kafka Dataset: A definition of a dataset to get training data from Kafka.

PyTorch Kafka Dataset: A definition of a dataset to get training data from Kafka.

ERTIS Research Group 7 Aug 01, 2022
Code release for NeX: Real-time View Synthesis with Neural Basis Expansion

NeX: Real-time View Synthesis with Neural Basis Expansion Project Page | Video | Paper | COLAB | Shiny Dataset We present NeX, a new approach to novel

538 Jan 09, 2023
A keras-based real-time model for medical image segmentation (CFPNet-M)

CFPNet-M: A Light-Weight Encoder-Decoder Based Network for Multimodal Biomedical Image Real-Time Segmentation This repository contains the implementat

268 Nov 27, 2022
Source code and data from the RecSys 2020 article "Carousel Personalization in Music Streaming Apps with Contextual Bandits" by W. Bendada, G. Salha and T. Bontempelli

Carousel Personalization in Music Streaming Apps with Contextual Bandits - RecSys 2020 This repository provides Python code and data to reproduce expe

Deezer 48 Jan 02, 2023
Smart edu-autobooking - Johnson @ DMI-UNICT study room self-booking system

smart_edu-autobooking Sistema di autoprenotazione per l'aula studio [email protected]

Davide Carnemolla 17 Jun 20, 2022
Multiple Object Tracking with Yolov5!

Tracking with yolov5 This implementation is for who need to tracking multi-object only with detector. You can easily track mult-object with your well

9 Nov 08, 2022
🍷 Gracefully claim weekly free games and monthly content from Epic Store.

EPIC 免费人 🚀 优雅地领取 Epic 免费游戏 Introduction 👋 Epic AwesomeGamer 帮助玩家优雅地领取 Epic 免费游戏。 使用 「Epic免费人」可以实现如下需求: get:搬空游戏商店,获取所有常驻免费游戏与免费附加内容; claim:领取周免游戏及其免

571 Dec 28, 2022
Code for Deep Single-image Portrait Image Relighting

Deep Single-Image Portrait Relighting [Project Page] Hao Zhou, Sunil Hadap, Kalyan Sunkavalli, David W. Jacobs. In ICCV, 2019 Overview Test script for

438 Jan 05, 2023
MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble

datasketch: Big Data Looks Small datasketch gives you probabilistic data structures that can process and search very large amount of data super fast,

Eric Zhu 1.9k Jan 07, 2023
Code for "Single-view robot pose and joint angle estimation via render & compare", CVPR 2021 (Oral).

Single-view robot pose and joint angle estimation via render & compare Yann Labbé, Justin Carpentier, Mathieu Aubry, Josef Sivic CVPR: Conference on C

Yann Labbé 51 Oct 14, 2022
The official implementation of NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [ICLR-2021]. https://arxiv.org/pdf/2101.12378.pdf

NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [ICLR-2021] Release Notes The offical PyTorch implementation of NeMo, p

Angtian Wang 76 Nov 23, 2022
Block-wisely Supervised Neural Architecture Search with Knowledge Distillation (CVPR 2020)

DNA This repository provides the code of our paper: Blockwisely Supervised Neural Architecture Search with Knowledge Distillation. Illustration of DNA

Changlin Li 215 Dec 19, 2022
EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation (CVPR'21)

EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation (CVPR'21) Citation If y

addisonwang 18 Nov 11, 2022