ConvNets created with Keras.
Read more about these models on MachineCurve
- For the 3D CNN (
3d_cnn.py): https://www.machinecurve.com/index.php/2019/10/18/a-simple-conv3d-example-with-keras/ - For the BatchNormalization CNN (
model_batchnorm.py): https://www.machinecurve.com/index.php/2020/01/15/how-to-use-batch-normalization-with-keras/ - For the CIFAR10 TensorBoard CNN (
model_cifar10_tensorboard.py): https://www.machinecurve.com/index.php/2019/11/13/how-to-use-tensorboard-with-keras/ - For the CNN with sparse categorical crossentropy (
model_sparse.py): https://www.machinecurve.com/index.php/2019/10/06/how-to-use-sparse-categorical-crossentropy-in-keras - For the depthwise separable CNN (
model_depthwise_separated.py): https://www.machinecurve.com/index.php/2019/09/24/creating-depthwise-separable-convolutions-in-keras/ - For the Dropout CNN (
model_dropout.py& comparison): https://www.machinecurve.com/index.php/2019/12/18/how-to-use-dropout-with-keras/ - For the ELU CNN (
model_elu.py& comparison): https://www.machinecurve.com/index.php/2019/12/09/how-to-use-elu-with-keras/ - For the FTSwish CNN (
model_ftswish.py& comparison): https://www.machinecurve.com/index.php/2020/01/06/how-to-use-ftswish-with-keras/ - For the KL divergence CNN (
model_kl_divergence_comp.py): https://www.machinecurve.com/index.php/2019/12/21/how-to-use-kullback-leibler-divergence-kl-divergence-with-keras/ - For the Leaky ReLU CNN (
model_leaky_relu.py): https://www.machinecurve.com/index.php/2019/11/12/using-leaky-relu-with-keras/ - For the LiSHT CNN (
model_lisht.py/model_lisht_compare.py): https://www.machinecurve.com/index.php/2019/11/17/how-to-use-lisht-activation-function-with-keras/ - For the normal CNN (
model.py): https://www.machinecurve.com/index.php/2019/09/17/how-to-create-a-cnn-classifier-with-keras - For the PReLU CNN (
model_prelu.py& comparison): https://www.machinecurve.com/index.php/2019/12/05/how-to-use-prelu-with-keras/
Datasets:
- http://yann.lecun.com/exdb/mnist/
- https://pypi.org/project/extra-keras-datasets/
- Clanuwat, T., Bober-Irizar, M., Kitamoto, A., Lamb, A., Yamamoto, K., & Ha, D. (2018). Deep learning for classical Japanese literature. arXiv preprint arXiv:1812.01718. Retrieved from https://arxiv.org/abs/1812.01718