Introduction to PyTorch
summary
Hands‑on PyTorch code runs on Google Colab with GPU and a linked GitHub repo; examples include a toy adding network (learning takes ~2,000 training samples), a rotation‑matrix generator that improves with deeper nets, a small CNN on CIFAR‑10 reaching ~50% after three epochs, and ResNet50 transfer learning that hits ~89% validation accuracy from ~250 images. Also covers RNN/LSTM text generation (Shakespeare and Trump tweets), optimizer choices (Adam), and practical save/load workflows.
AI-written summary · about
chapters (9)
- 0:00PyTorch setup
- 12:09What is PyTorch and tensors
- 20:21Simple neural network
- 33:37Activation functions
- 46:57Image recognition with CNNs
- 1:00:15Transfer learning for classification
- 1:14:57RNNs and language models
- 1:28:12Text generation with RNNs
- 1:32:22Q&A
related talks
01h 27mHands-On Computer Vision with PyTorch
01h 40mA Deep Dive into NLP with PyTorch
01h 39mGoogle Colaboratory and Python: Deep Learning basics for CV tasks
20mLearn You a PyTorch!
01h 07mComputer Vision with PyTorch
06mPyTorch 1.2 and PyTorch Hub: A Quick Introduction
47mDeep Learning with PyTorch
47mGet to Know PyTorch - A Cutting Edge Open Source AI Framework for Deep Learning