https://github.com/calmisential/Basic_CNNs_TensorFlow2

A tensorflow2 implementation of some basic CNNs(MobileNetV1/V2/V3, EfficientNet, ResNeXt, InceptionV4, InceptionResNetV1/V2, SENet, SqueezeNet, DenseNet, ShuffleNetV2, ResNet).
https://github.com/calmisential/Basic_CNNs_TensorFlow2

densenet efficientnet image-classification image-recognition inception-resnet-v2 inception-v4 mobilenet-v1 mobilenet-v2 mobilenet-v3 regnet resnet resnext senet seresnet shufflenet-v2 squeezenet tensorflow tensorflow2

Last synced: about 1 month ago
JSON representation

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

• Host: GitHub
• URL: https://github.com/calmisential/Basic_CNNs_TensorFlow2
• Owner: calmiLovesAI
• License: mit
• Created: 2019-09-11T07:43:19.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2021-11-24T04:27:38.000Z (almost 3 years ago)
• Last Synced: 2024-05-20T10:10:18.469Z (4 months ago)
• Topics: densenet, efficientnet, image-classification, image-recognition, inception-resnet-v2, inception-v4, mobilenet-v1, mobilenet-v2, mobilenet-v3, regnet, resnet, resnext, senet, seresnet, shufflenet-v2, squeezenet, tensorflow, tensorflow2
• Language: Python
• Homepage:
• Size: 148 KB
• Stars: 522
• Watchers: 19
• Forks: 177
• Open Issues: 27
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-tensorflow-2 - A tensorflow2 implementation of some basic CNNs(MobileNetV1/V2/V3, EfficientNet, ResNeXt, InceptionV4, InceptionResNetV1/V2, SENet, SqueezeNet, DenseNet, ShuffleNetV2, ResNet).

README

        
# Basic_CNNs_TensorFlow2

A tensorflow2 implementation of some basic CNNs.

## Networks included:

+ MobileNet_V1

+ MobileNet_V2

+ [MobileNet_V3](https://github.com/calmisential/MobileNetV3_TensorFlow2)

+ [EfficientNet](https://github.com/calmisential/EfficientNet_TensorFlow2)

+ [ResNeXt](https://github.com/calmisential/ResNeXt_TensorFlow2)

+ [InceptionV4, InceptionResNetV1, InceptionResNetV2](https://github.com/calmisential/InceptionV4_TensorFlow2)

+ SE_ResNet_50, SE_ResNet_101, SE_ResNet_152, SE_ResNeXt_50, SE_ResNeXt_101

+ SqueezeNet

+ [DenseNet](https://github.com/calmisential/DenseNet_TensorFlow2)

+ ShuffleNetV2

+ [ResNet](https://github.com/calmisential/TensorFlow2.0_ResNet)

+ RegNet

## 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 >= 3.9

+ Tensorflow >= 2.7.0

+ tensorflow-addons >= 0.15.0

2. 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

```

3. 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

 ```

4. Run **to_tfrecord.py** to generate tfrecord files.

5. Change the corresponding parameters in **config.py**.

6. Run **show_model_list.py** to get the index of model.

7. Run **python train.py --idx [index]** to start training.


If you want to train the *EfficientNet*, you should change the IMAGE_HEIGHT and IMAGE_WIDTH before training.

- b0 = (224, 224)

- b1 = (240, 240)

- b2 = (260, 260)

- b3 = (300, 300)

- b4 = (380, 380)

- b5 = (456, 456)

- b6 = (528, 528)

- b7 = (600, 600)

## Evaluate

Run **python evaluate.py --idx [index]** 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)

     

     

          SEResNeXt

          SEResNeXt50

          (224 * 224)

     

     

          SEResNeXt101

          (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](https://arxiv.org/abs/1704.04861)

2. MobileNet_V2: [Inverted Residuals and Linear Bottlenecks](https://arxiv.org/abs/1801.04381)

3. MobileNet_V3: [Searching for MobileNetV3](https://arxiv.org/abs/1905.02244)

4. EfficientNet: [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://arxiv.org/abs/1905.11946)

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](https://arxiv.org/abs/1611.05431)

7. Inception_V4/Inception_ResNet_V1/Inception_ResNet_V2: [Inception-v4,  Inception-ResNet and the Impact of Residual Connectionson Learning](https://arxiv.org/abs/1602.07261)

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](https://arxiv.org/abs/1709.01507)

11. SqueezeNet: [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://arxiv.org/abs/1602.07360)

12. DenseNet: [Densely Connected Convolutional Networks](https://arxiv.org/abs/1608.06993)

13. https://zhuanlan.zhihu.com/p/37189203

14. ShuffleNetV2: [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

](https://arxiv.org/abs/1807.11164)

15. https://zhuanlan.zhihu.com/p/48261931

16. ResNet: [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385)

17. RegNet: [Designing Network Design Spaces](https://arxiv.org/abs/2003.13678)