/Basic_CNNs_TensorFlow2

A tensorflow2 implementation of some basic CNNs(MobileNetV1/V2/V3, EfficientNet, ResNeXt, InceptionV4, InceptionResNetV1/V2, SENet, SqueezeNet, DenseNet, ShuffleNetV2, ResNet).

Primary LanguagePythonMIT LicenseMIT

Basic_CNNs_TensorFlow2

A tensorflow2 implementation of some basic CNNs.

Networks included:

Other networks

For AlexNet and VGG, see : https://github.com/calmisential/TensorFlow2.0_Image_Classification
For InceptionV3, see : https://github.com/calmisential/TensorFlow2.0_InceptionV3
For ResNet, see : https://github.com/calmisential/TensorFlow2.0_ResNet

Train

  1. Requirements:
  • Python >= 3.6
  • Tensorflow == 2.1.0
  1. To train the network on your own dataset, you can put the dataset under the folder original dataset, and the directory should look like this:
|——original dataset
   |——class_name_0
   |——class_name_1
   |——class_name_2
   |——class_name_3
  1. Run the script split_dataset.py to split the raw dataset into train set, valid set and test set. The dataset directory will be like this:
|——dataset
  |——train
       |——class_name_1
       |——class_name_2
       ......
       |——class_name_n
  |——valid
       |——class_name_1
       |——class_name_2
       ......
       |——class_name_n
  |—-test
       |——class_name_1
       |——class_name_2
       ......
       |——class_name_n
  1. Run to_tfrecord.py to generate tfrecord files.
  2. Change the corresponding parameters in config.py.
  3. Run train.py to start training.
    If you want to train the EfficientNet, you should change the IMAGE_HEIGHT and IMAGE_WIDTH to resolution in the params, and then run train.py to start training.

Evaluate

Run evaluate.py to evaluate the model's performance on the test dataset.

Different input image sizes for different neural networks

Type Neural Network Input Image Size (height * width)
MobileNet MobileNet_V1 (224 * 224)
MobileNet_V2 (224 * 224)
MobileNet_V3 (224 * 224)
EfficientNet EfficientNet(B0~B7) /
ResNeXt ResNeXt50 (224 * 224)
ResNeXt101 (224 * 224)
Inception InceptionV4 (299 * 299)
Inception_ResNet_V1 (299 * 299)
Inception_ResNet_V2 (299 * 299)
SE_ResNet SE_ResNet_50 (224 * 224)
SE_ResNet_101 (224 * 224)
SE_ResNet_152 (224 * 224)
SqueezeNet SqueezeNet (224 * 224)
DenseNet DenseNet_121 (224 * 224)
DenseNet_169 (224 * 224)
DenseNet_201 (224 * 224)
DenseNet_269 (224 * 224)
ShuffleNetV2 ShuffleNetV2 (224 * 224)
ResNet ResNet_18 (224 * 224)
ResNet_34 (224 * 224)
ResNet_50 (224 * 224)
ResNet_101 (224 * 224)
ResNet_152 (224 * 224)

References

  1. MobileNet_V1: Efficient Convolutional Neural Networks for Mobile Vision Applications
  2. MobileNet_V2: Inverted Residuals and Linear Bottlenecks
  3. MobileNet_V3: Searching for MobileNetV3
  4. EfficientNet: EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
  5. The official code of EfficientNet: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
  6. ResNeXt: Aggregated Residual Transformations for Deep Neural Networks
  7. Inception_V4/Inception_ResNet_V1/Inception_ResNet_V2: Inception-v4, Inception-ResNet and the Impact of Residual Connectionson Learning
  8. The official implementation of Inception_V4: https://github.com/tensorflow/models/blob/master/research/slim/nets/inception_v4.py
  9. The official implementation of Inception_ResNet_V2: https://github.com/tensorflow/models/blob/master/research/slim/nets/inception_resnet_v2.py
  10. SENet: Squeeze-and-Excitation Networks
  11. SqueezeNet: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
  12. DenseNet: Densely Connected Convolutional Networks
  13. https://zhuanlan.zhihu.com/p/37189203
  14. ShuffleNetV2: ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
  15. https://zhuanlan.zhihu.com/p/48261931
  16. ResNet: Deep Residual Learning for Image Recognition

下载Miniconda3-latest-Linux-x86_64.sh

安装conda bash Miniconda3-latest-Linux-x86_64.sh

设置conda开机时取消进入虚拟环境 conda config --set auto_activate_base false

替换conda源为清华源 conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/ conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/ conda config --set show_channel_urls yes vim ~/.condarc

创建python3.6 tensorflow2.1的conda虚拟环境 conda create -n py3.6_tf2.1.0 python=3.6

进入环境 conda activate py3.6-tf2.1.0

拉取训练代码 https://github.com/CraneLu/Basic_CNNs_TensorFlow2.git

后台运行，日志输出到log目录下 nohup python -u train.py > log/train.log &