Note: in the module we use TensorFlow+Keras. These videos were recorded a while ago, and while they are still relevant, PyTorch became the to-go framework for training neural networks.
That's why we also re-recorded the content of this module with PyTorch. You can find the materials in the pytorch/ folder.
We don't go over the theory in the PyTorch part. For that, refer to the main module (the one that still uses Keras).
How to watch it:
- If you want to learn PyTorch only, watch the module content for the theory only and then follow along the content of the PyTorch part
- If you want to learn both (and have time), first do the module and then the PyTorch part
TensorFlow module videos:
- 8.1 Fashion classification
- 8.2 TensorFlow and Keras
- 8.3 Pre-trained convolutional neural networks
- 8.4 Convolutional neural networks
- 8.5 Transfer learning
- 8.6 Adjusting the learning rate
- 8.7 Checkpointing
- 8.8 Adding more layers
- 8.9 Regularization and dropout
- 8.10 Data augmentation
- 8.11 Training a larger model
- 8.12 Using the model
- 8.13 Summary
- 8.14 Explore more
- 8.15 Homework
Did you take notes? You can share them here (or in each unit separately)
- Alvaro Navas' Notes
- Kwang Yang's Notes on PyTorch
- Notes from froukje
- Saturn Cloud setup
- Connecting Github, Saturn Cloud and local VSCode via SSH
- Gradio demonstration with Huggingface Space
- Hyperparameter Search With Keras-tuners
- Installation of tensorflow v2.14 in WSL2 and Ubuntu 22.04 with Nvidia GPU
- Notes from Peter Ernicke
- Notes from Kemal Dahha
- Notes from Maximilien Eyengue
- Notes from Revathy Ramalingam
- Add your notes here