中文教程:
[BLOG] https://www.steamforfun.cn/?p=413
[CSDN] http://t.csdn.cn/XNsTS
@[TOC](Simple Tensorflow Image Classification)
Image classification by tensorflow and opencv.
Only four python scripts can complete the training and deployment of custom model.
preprocess.py: Rename & Resize pictures
train.py: Generate dataset and Train
test_model.py: Check the Performance of the new model
deploy.py: Use camera to run the new model
Install the item named "C++ for Desktop Development".
// Run Anaconda Prompt, coding...
conda create -n tensorflow python>3.8
activate tensorflow
pip install tensorflow>2.8
pip install labelImg
pip install opencv-python
pip install pillow
1.Put images in folder named "voc_dataset", subfolders named "classes_index".
2.Run "preprocess.py" to rename and resize the images.
3.Run labelImg to annotate all the images.
4.Run "train.py" to generate a new model.
5.Run "test_model.py" to test the accuracy of model.
6.Run "deploy.py" on computer or embedded device to classify object real-time.