Enter to search with the selected external provider · Press / anywhere to focus search
Enter opens your selected web provider in a new tab
External jump (enhancement)
Enter = open in new tab
Strengths
- Completely free, includes course videos and code
- Practice first, write code first and then understand theory
- The fastai library makes deep learning code extremely concise
- Equipped with Jupyter Notebook, you can learn and practice at the same time
- Active community, good forum support
Best for
- People with programming background learn deep learning
- Quickly get started with PyTorch and deep learning practices
- Learn computer vision and NLP applications
- Learn best practices for deep learning
- Preparing for a Kaggle competition
Course structure and learning path
Fast.ai adopts a "top-down" learning method, running the code first and then understanding the principles.
Scenario
Start the Practical Deep Learning course
Prompt example
Course address: course.fast.ai
Lesson 1: Start with image classification
1. Open Jupyter Notebook (Kaggle or Colab recommended)
2. Run the first code example:
```python
from fastai.vision.all import *
# Download dataset
path = untar_data(URLs.PETS)
#Create data loader
dls = ImageDataLoaders.from_name_re(
path, get_image_files(path/"images"),
pat=r'([^/]+)_\d+.jpg$',
item_tfms=Resize(460),
batch_tfms=aug_transforms(size=224)
)
#Train model
learn = vision_learner(dls, resnet34, metrics=error_rate)
learn.fine_tune(3)
```
3. After a few minutes, the model training is completed
4. Accuracy usually exceeds 90%Output / what to expect
Trained a pet breed classifier in less than 10 lines of code,
Accuracy rate exceeds 90%,
This is the charm of Fast.ai: let you see the effect first, and then explain the principle.
Tips
It is recommended to run the code on Kaggle. The free GPU quota is enough for learning.
Scenario
Take an NLP course
Prompt example
Fast.ai NLP Course (Part 3 of course.fast.ai):
1. Introduction to text classification:
```python
from fastai.text.all import *
# Load IMDb data set
path = untar_data(URLs.IMDB)
dls = TextDataLoaders.from_folder(path, valid='test')
# Train language model
learn = text_classifier_learner(
dls, AWD_LSTM, drop_mult=0.5, metrics=accuracy
)
learn.fine_tune(4, 1e-2)
```
2. Understand the Transformer architecture
3. Implement a simple attention mechanism from scratchOutput / what to expect
Learn NLP from practice,
Run the code first to see the effect.
Learn more about the principles behind it.
Tips
Fast.ai’s NLP course is a great introduction to Transformer.