图像分类集成以下模型:ResNet18、ResNet34、ResNet50、ResNet101、ResNet152、 VGG16、VGG19、InceptionV3、Xception、MobileNet、AlexNet、LeNet、ZF_Net、DenseNet,在config.py里面选择使用哪种模型,目前本人亲测,残差网络resnet的效果比较好。
- VGG16
- VGG19
- InceptionV3
- Xception
- MobileNet
- AlexNet
- LeNet
- ZF_Net
- ResNet18
- ResNet34
- ResNet50
- ResNet101
- ResNet152
- DenseNet(dismissed this time)
"train and test data set folder is:"
/path/classes1/cat*.jpg,
/path/classes2/dog*.jpg,
/path/classes3/people*.jpg,
/path/classes4/*.jpg,
- Attentions ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! !
- classes name must be contained in folder name
My environment is based on
- ubuntu16
- cuda8 (cuda9.0)
- tensorflow_gpu1.4 (tensorflow_gpu1.10 )
- keras2.0.8
- numpy
- tqdm
- opencv-python
- scikit-learn
- pip3 install tensorflow_gpu==1.4
- pip3 install keras==2.0.8
- pip3 install numpy
- pip3 install tqdm
- pip3 install opencv-python
- pip3 install scikit-learn
- python3 mk_class_idx.py
- python3 train.py
- python3 predict.py classes_name
Author email: mymailwith163@163.com