MNIST_deeplearning_recognition
Deeplearning model trained with Keras and Tensorflow to recognise the MNIST dataset.
-
First Best-Performing Network Architecture (Ensemble):
-
Second Best-Performing Network Architecture (Ensemble)
Both of the shown architectures perform the same, at 99.71% accuracy.
For more information and in-depth metrics, check the Model Performance EXCEL file present in the root directory or check the following table:
Resources:
- https://towardsdatascience.com/setting-up-tensorflow-gpu-with-cuda-and-anaconda-onwindows-2ee9c39b5c44
- https://machinelearningmastery.com/how-to-develop-a-convolutional-neural-network-from-scratch-for-mnist-handwritten-digit-classification/
- https://medium.com/@nrk25693/how-to-add-your-conda-environment-to-your-jupyter-notebook-in-just-4-steps-abeab8b8d084
- https://medium.com/@alexppppp/how-to-train-an-ensemble-of-convolutional-neural-networks-for-image-classification-8fc69b087d3
- https://stackoverflow.com/questions/42635310/remove-kernel-on-jupyter-notebook
- https://stackoverflow.com/questions/49127834/removing-conda-environment
- https://conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html
- https://stackoverflow.com/questions/72441758/typeerror-descriptors-cannot-not-be-created-directly
- https://medium.com/the-data-science-publication/how-to-augment-the-mnist-dataset-using-tensorflow-4fbf113e99a0
- https://machinelearningmastery.com/batch-normalization-for-training-of-deep-neural-networks/
- https://www.tensorflow.org/guide/gpu_performance_analysis
- https://aakashgoel12.medium.com/how-to-add-user-defined-function-get-f1-score-in-keras-metrics-3013f979ce0d
- https://scikit-learn.org/stable/modules/model_evaluation.html