PyTorch_YOLO_Tutorial

YOLO Tutorial

Introduction

Here is the source code for an introduction to YOLO. We adopted the core concepts of YOLOv1~v4, YOLOX and YOLOv7 for this project and made the necessary adjustments. By learning how to construct the well-known YOLO detector, we hope that newcomers can enter the field of object detection without any difficulty.

Book: The technical books that go along with this project's code is being reviewed, please be patient.

Requirements

We recommend you to use Anaconda to create a conda environment:
```
conda create -n yolo python=3.6
```
Then, activate the environment:
```
conda activate yolo
```
Requirements:
```
pip install -r requirements.txt 
```

My environment:

PyTorch = 1.9.1
Torchvision = 0.10.1

At least, please make sure your torch is version 1.x.

Training Configuration

Configuration
Per GPU Batch Size	16
Init Lr	0.01
Warmup Scheduler	Linear
Lr Scheduler	Linear
Optimizer	SGD
Multi Scale Train	True

Experiments

VOC

Download VOC.

cd <PyTorch_YOLO_Tutorial>
cd dataset/scripts/
sh VOC2007.sh
sh VOC2012.sh

Check VOC

cd <PyTorch_YOLO_Tutorial>
python dataset/voc.py

Train on VOC

For example:

python train.py --cuda -d voc --root path/to/VOCdevkit -v yolov1 -bs 16 --max_epoch 150 --wp_epoch 1 --eval_epoch 10 --fp16 --ema --multi_scale

All models are trained with ImageNet pretrained weight (IP). All FLOPs are measured with a 640x640 image size on VOC2007 test. The FPS is measured with batch size 1 on 3090 GPU from the model inference to the NMS operation.

COCO

Download COCO.

cd <PyTorch_YOLO_Tutorial>
cd dataset/scripts/
sh COCO2017.sh

Check COCO

cd <PyTorch_YOLO_Tutorial>
python dataset/coco.py

Train on COCO

For example:

python train.py --cuda -d coco --root path/to/COCO -v yolov1 -bs 16 --max_epoch 150 --wp_epoch 1 --eval_epoch 10 --fp16 --ema --multi_scale

Model	Backbone	Scale	IP	Epoch	AP^val 0.5	FLOPs ^(G)	Params ^(M)	Weight
YOLOv1	ResNet-18	640	√	150	76.7	37.8	21.3	ckpt
YOLOv2	DarkNet-19	640	√	150	79.8	53.9	30.9	ckpt
YOLOv3	DarkNet-53	640	√	150	82.0	167.4	54.9	ckpt
YOLOv4	CSPDarkNet-53	640	√	150	83.6	162.7	61.5	ckpt
YOLOv5	CSPDarkNet-L	640	√	150	83.8	155.6	54.2	ckpt
YOLOX	CSPDarkNet-L	640	√	150	84.6	155.4	54.2	ckpt
YOLOv7-Large	ELANNet-Large	640	√	150	85.5	144.6	44.0	ckpt

All models are trained with ImageNet pretrained weight (IP). All FLOPs are measured with a 640x640 image size on COCO val2017. The FPS is measured with batch size 1 on 3090 GPU from the model inference to the NMS operation.

Due to my limited computing resources, I had to abandon training on other YOLO detectors, including YOLOv7-Huge, YOLOv8-Small, YOLOv8-Medium, YOLOv8-Large and YOLOv8-Huge. If you are interested in these models and have trained them using the code from this project, I would greatly appreciate it if you could share the trained weight files with me.

Train

Single GPU

sh train.sh

You can change the configurations of train.sh, according to your own situation.

You also can add --vis_tgt to check the images and targets during the training stage. For example:

python train.py --cuda -d coco --root path/to/coco -v yolov1 --vis_tgt

Multi GPUs

sh train_ddp.sh

You can change the configurations of train_ddp.sh, according to your own situation.

In the event of a training interruption, you can pass --resume the latest training weight path (None by default) to resume training. For example:

python train.py \
        --cuda \
        -d coco \
        -v yolov1 \
        -bs 16 \
        --max_epoch 300 \
        --wp_epoch 3 \
        --eval_epoch 10 \
        --ema \
        --fp16 \
        --resume weights/coco/yolov1/yolov1_epoch_151_39.24.pth

Then, training will continue from 151 epoch.

Test

python test.py -d coco \
               --cuda \
               -v yolov1 \
               --img_size 640 \
               --weight path/to/weight \
               --root path/to/dataset/ \
               --show

Evaluation

python eval.py -d coco-val \
               --cuda \
               -v yolov1 \
               --img_size 640 \
               --weight path/to/weight \
               --root path/to/dataset/ \
               --show

Demo

I have provide some images in data/demo/images/, so you can run following command to run a demo:

python demo.py --mode image \
               --path_to_img data/demo/images/ \
               -v yolov1 \
               --img_size 640 \
               --cuda \
               --weight path/to/weight

If you want run a demo of streaming video detection, you need to set --mode to video, and give the path to video --path_to_vid。

python demo.py --mode video \
               --path_to_img data/demo/videos/your_video \
               -v yolov1 \
               --img_size 640 \
               --cuda \
               --weight path/to/weight

If you want run video detection with your camera, you need to set --mode to camera。

python demo.py --mode camera \
               -v yolov1 \
               --img_size 640 \
               --cuda \
               --weight path/to/weight

Model	Backbone	Scale	IP	Epoch	AP^val 0.5:0.95	AP^val 0.5	Weight
YOLOv1	ResNet-18	640	√	150	27.9	47.5	ckpt
YOLOv2	DarkNet-19	640	√	150	32.7	50.9	ckpt
YOLOv3	DarkNet-53	640	√	250	42.9	63.5	ckpt
YOLOv4	CSPDarkNet-L	640	√	250	46.6	65.8	ckpt
YOLOv5	CSPDarkNet-53	640	√	250
YOLOX	CSPDarkNet-L	640	√	300	46.6	66.1	ckpt
YOLOv7-Tiny	ELANNet-Tiny	640	√	300
YOLOv7-Large	ELANNet-Large	640	√	300
YOLOv8-Nano	CSP-ELANNet-Nano	640	√	500

README.md 9.2 KB Histórico Raw