CS 591 Deep learning Project
Description of files:
-
Effnetb6.ipynb & effnetb7.ipynb: Used for training models -
inference-kernel.ipynb: Submitted to Kaggle to check QWK score -
preprocess_dataprep.ipynb: Augmentations and pre-processing of images -
plots.ipynb: Used to plot final result and training data
Code References:
-
https://towardsdatascience.com/setting-up-kaggle-in-google-colab-ebb281b61463
-
EfficientNet code: https://github.com/qubvel/efficientnet
Paper References:
-
Tan, Mingxing, and Quoc V. Le. "Efficientnet: Rethinking model scaling for convolutional neural networks." arXiv preprint arXiv:1905.11946 (2019).
-
Ramachandran, Prajit, Barret Zoph, and Quoc V. Le. "Searching for activation functions." arXiv preprint arXiv:1710.05941 (2017). He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
-
He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
-
Sandler, Mark, et al. "Mobilenetv2: Inverted residuals and linear bottlenecks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.
-
Hu, Jie, Li Shen, and Gang Sun. "Squeeze-and-excitation networks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.
-
Gulshan, Varun, et al. "Performance of a deep-learning algorithm vs manual grading for detecting diabetic retinopathy in india." JAMA ophthalmology 137.9 (2019): 987-993.