Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
code for deep learning courses
| Date | Stars |
|---|---|
| 2026-07-24 | 1264 |
| 2026-07-25 | 1264 |
| 2026-07-28 | 1264 |
| 2026-07-30 | 1264 |
| 2026-07-31 | 1265 |
| 2026-08-06 | 1265 |
Today
— stars today
This week
+1 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.08%/day
# [Dataflowr: Deep Learning DIY](https://dataflowr.github.io/website/) [](https://dataflowr.github.io/website/) Code and notebooks for the deep learning course [dataflowr](https://dataflowr.github.io/website/). Here is the schedule followed at école polytechnique in 2023: ## :sunflower:Session:one: Finetuning VGG >- [Module 1 - Introduction & General Overview](https://dataflowr.github.io/website/modules/1-intro-general-overview/) Slides + notebook Dogs and Cats with VGG + Practicals (more dogs and cats) <details> <summary>Things to remember</summary> > - you do not need to understand everything to run a deep learning model! But the main goal of this course will be to come back to each step done today and understand them... > - to use the dataloader from Pytorch, you need to follow the API (i.e. for classification store your dataset in folders) > - using a pretrained model and modifying it to adapt it to a similar task is easy. > - if you do not understand why we take this loss, that's fine, we'll cover that in Module 3. > - even with a GPU, avoid unnecessary computations! </details> ## :sunflower:Session:two: PyTorch tensors and Autodiff >- [Module 2a - PyTorch tensors](https://dataflowr.github.io/website/modules/2a-pytorch-tensors/) >- [Module 2b - Automatic differentiation](https://dataflowr.github.io/website/modules/2b-automatic-differentiation/) + Practicals >- MLP from scratch start of [HW1](https://dataflowr.github.io/website/homework/1-mlp-from-scratch/) >- [another look at autodiff with dual numbers and Julia](https://github.com/dataflowr/notebooks/blob/master/Module2/AD_with_dual_numbers_Julia.ipynb) <details> <summary>Things to remember</summary> >- Pytorch tensors = Numpy on GPU + gradients! >- in deep learning, [broadcasting](https://numpy.org/doc/stable/user/basics.broadcasting.html) is used everywhere. The rules are the same as for Numpy. >- Automatic differentiation is not only the chain rule! Backpropagation algorithm (or dual numbers) is a clever algorithm to implement automatic differentiation... </details> ## :sunflower:Session:three: > - [Module 3 - Loss function for classification](https://dataflowr.github.io/website/modules/3-loss-functions-for-classification/) > - [Module 4 - Optimization for deep learning](https://dataflowr.github.io/website/modules/4-optimization-for-deep-learning/) > - [Module 5 - Stacking layers](https://dataflowr.github.io/website/modules/5-stacking-layers/) and overfitting a MLP on CIFAR10: [Stacking_layers_MLP_CIFAR10.ipynb](https://github.com/dataflowr/notebooks/blob/master/Module5/Stacking_layers_MLP_CIFAR10.ipynb) > - [Module 6: Convolutional neural network](https://dataflowr.github.io/website/modules/6-convolutional-neural-network/) > - how to regularize with dropout and uncertainty estimation with MC Dropout: [Module 15 - Dropout](https://dataflowr.github.io/website/modules/15-dropout/) <details> <summary>Things to remember</summary> >- Loss vs Accuracy. Know your loss for a classification task! >- know your optimizer (Module 4) >- know how to build a neural net with torch.nn.module (Module 5) >- know how to use convolution and pooling layers (kernel, stride, padding) >- know how to use dropout </details> ## :sunflower:Session:four: > - [Module 7 - Dataloading](https://dataflowr.github.io/website/modules/7-dataloading/) > - [Module 8a - Embedding layers](https://dataflowr.github.io/website/modules/8a-embedding-layers/) > - [Module 8b - Collaborative filtering](https://dataflowr.github.io/website/modules/8b-collaborative-filtering/) and build your own recommender system: [08_collaborative_filtering_empty.ipynb](https://github.com/dataflowr/notebooks/blob/master/Module8/08_collaborative_filtering_empty.ipynb) (on a larger dataset [08_collaborative_filtering_1M.ipynb](https://github.com/dataflowr/notebooks/blob/master/Module8/08_collaborative_filtering_1M
Excerpt of 18,388 characters
Read on GitHub
416
40
Pietro Monticone · Harmonic · United States
26
18
Jill-Jênn Vie · Inria · France
15
Benjamin Loison · Agence Ministérielle pour l'IA de Défense
7
3
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9080314970ee90ce, topic:deep-learning, topic:pytorch, readme:automatic differentiation