In this repo I have created basic to moderate important concepts of PyTorch frameworks that necessary for Neural Networks with python!
For every model I have showed Training, Validation steps and logs in console, tested the custom dataset test images using model.predict()
Highly useful for revision of pytorch concepts from basic to moderate concepts in quick time.
Just follow the given files for clear idea on concepts and if you want conceptual theory go through the PyTorch tutorial then the scripts simultaniouly for better understanding.
!Look out to discription.txt for topics discussed on each .ipynb file
1. Tensor Basics -> torch_basics\pytorch_intro.ipynb
overview on tensor operations -> torch_basics\overview_yt.ipynb
2. Gradient Claculations with Autograd -> backpropagation.ipynb
3. Backpropagation -> backpropagation.ipynb
4. Gradient Decentwith Autograd and Backpropagation -> backpropagation.ipynb
5. Training Pipeline: Model, Loss, Optimizer -> backpropagation.ipynb
6. Linear Regression -> linear_regression.ipynb
7. Logistic Regression -> logistic_regression.ipynb
8. Dataset and DataLoader-Batch Training -> dataset_batch.ipynb
9. Dataset Transforms -> dataset_transform.ipynb
10. Softmax and Cross Entropy -> softmax_crossentropy.ipynb
11. Activation Function -> activation.ipynb
12. FeedForward Neural Networks -> feedforward.ipynb
13. Convolutional Neural Networks -> cnn.ipynb
14. How to use the TensorBoard -> feedforward - tensorboard.ipynb
15. Saving and Loading Models -> saving_model.ipynb
16. RNN - Name classification using Recurrent Neural Net -> rnn folder
17. RNN & LSTM & GRU -> manual_rnn.ipynb
18. LR Scheduler (Learning Rate) -> transfer_learning.ipynb
Video tutorial playlist link: https://youtu.be/EMXfZB8FVUA?si=-qB7rhg95xa8VEq3
Praveen Sunkara!