I tried object detection with YOLO v3 (TensorFlow 2.0) on a windows CPU!
environment
windows7 64bit Gefore GTX 680MX GPU anaconda
Environmental preparation
Create keras_work with conda
conda create -n keras_work
activate keras_work
Install tensorflow, keras, pillow, matplotlib, opencv-python
conda install tensorflow
conda install keras
pip install pillow
conda install -c anaconda matplotlib
pip install opencv-python
windows git installation
conda install git
windows wget installation
conda install -c menpo wget
Material preparation
Get source from Github
cd c:\temp
git clone https://github.com/zzh8829/yolov3-tf2.git
cd yolov3-tf2
Download yolo3.weight from pjreddie.com
- It takes 2 hours
wget https://pjreddie.com/media/files/yolov3.weights --no-check-certificate
Since it is slow to get yolov3.weights from the above pjreddie.com, you can also download the following URL. https://pan.baidu.com/s/1G2Qh-V8kyLOq4oDbTwK6HQ Proposal (password): vogw The file is "yolo_tf2.1 \ data \ yolov3.weights"
Move yolo3.weight file to yolov3-tf2 path Confirm that the file has been moved
(keras_work) C:\temp\yolov3-tf2>dir /B *.weights
yolov3.weights
Convert (convert pre-trained darknet weight)
python convert.py --weights ./yolov3.weights --output ./checkpoints/yolov3.tf
Detection
python detect.py --image ./data/girl.png
Recommended Posts