Tidak Ada Deskripsi

4 Rilis

yjh0410 265a02bb77 fix a bug of COCOdataset		2 tahun lalu
config	6bf9fafba9 add YOLOX	2 tahun lalu
dataset	9d27a3ce43 train YOLOv2 on COCO	2 tahun lalu
evaluator	1d8f16cdaa modify loss of YOLOv1	2 tahun lalu
models	b1520f3a44 modify anchors of yolox	2 tahun lalu
utils	265a02bb77 fix a bug of COCOdataset	2 tahun lalu
.gitignore	ef7614c2de add ignore file	2 tahun lalu
README.md	b1520f3a44 modify anchors of yolox	2 tahun lalu
README_CN.md	11e84465c3 add README_CN	2 tahun lalu
engine.py	a0db6b97b7 train YOLOv1	2 tahun lalu
eval.py	6bf9fafba9 add YOLOX	2 tahun lalu
test.py	6bf9fafba9 add YOLOX	2 tahun lalu
train.py	6bf9fafba9 add YOLOX	2 tahun lalu
train.sh	b1520f3a44 modify anchors of yolox	2 tahun lalu

PyTorch_YOLO_Tutorial

YOLO Tutorial

English | 简体中文

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	Scale	IP	Epoch	AP50	FLOPs ^(G)	Params ^(M)	Weight
YOLOv1	640	√	150	76.7	37.8	21.3	ckpt
YOLOv2	640	√	150	79.8	53.9	30.9	ckpt
YOLOv3	640	√	150	82.0	167.4	54.9	ckpt
YOLOv4	640	√	150
YOLOX	640	√	150

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.

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	Scale	IP	Epoch
YOLOv1	640	√	150
YOLOv2	640	√	150
YOLOv3	640	√	250
YOLOv4	640	√	250
YOLOX	640	√	250

README.md