What I studied today:
- Recent Tendency of Using Models
- Using pretrained models to fine-tune on a specific task
- Saving a Model
- Can either save a the whole model or save only the parameters (smaller model)
- Practice with Code
- Saving a Checkpoint
- Utilizing the function for saving models, we can create a checkpoint at every iterations
- Transfer Learning
- Using a pretrained model on a larger dataset and fine-tuning on a specific, smaller dataset to obtain better results
- Freezing: frozing some of the parameters when tuning a pretrained model
- Monitoring Tools for PyTorch