Pinned Loading

1. tf2-cnn-mnist-classifier tf2-cnn-mnist-classifier Public

   CNN that classifies MNIST handwritten digits with TensorFlow 2 (Keras), reaching 98.36% test accuracy with a single convolutional layer and 105k parameters.

   Jupyter Notebook 1

2. tf2-neural-network-validation-regularization-iris tf2-neural-network-validation-regularization-iris Public

   Neural network classifier for the Iris dataset, built with TensorFlow 2 (Keras), focused on validation, regularisation (dropout, L2, batch normalisation) and training callbacks.

   Jupyter Notebook 1

3. tf2-svhn-digit-recognition tf2-svhn-digit-recognition Public

   MLP and CNN classifiers for the SVHN house-number digits dataset, built with TensorFlow 2 (Keras).

   Jupyter Notebook 1

4. tf2-transfer-learning-eurosat tf2-transfer-learning-eurosat Public

   CNN for EuroSAT satellite image classification, focused on checkpointing and reloading model weights with TensorFlow 2 / Keras.

   Jupyter Notebook 1

5. tf2-transfer-learning-cats-dogs tf2-transfer-learning-cats-dogs Public

   Cats vs dogs image classifier: a CNN trained from scratch vs transfer learning with a pretrained MobileNetV2. 98.7% test accuracy with TensorFlow 2 / Keras.

   Jupyter Notebook 1

6. tf2-image-data-pipelines-lsun-cifar100 tf2-image-data-pipelines-lsun-cifar100 Public

   Image classification with TensorFlow 2 / Keras: ImageDataGenerator with and without data augmentation on an LSUN subset, and a tf.data pipeline (filter, map, batch, shuffle) on a CIFAR-100 subset.

   Jupyter Notebook