Everything You Need to Know About Tensors in Deep Learning With PyTorch

This beginner workshop introduces tensors for deep learning with PyTorch in Python. It covers tensor creation, data types, conversions with NumPy and pandas, common operations, reshaping, concatenation, indexing, and CPU/GPU devices.

Syllabus

- Workshop Introduction
- Tensor Introduction
- Building blocks of Deep Learning
- Input data as Tensor
- Tensors as higher degree matrix
- Declaration of Tensors in PyTorch
- Tensor Data Types
- Tensors as Python List and Pandas DF
- Tensors from NumPy ndarray
- torch.ones_like function
- torch.zeros_like function
- Tensor to NumPy ndarray conversion
- Tensors Operations
- Matrix multiplication on Tensors
- Transpose
- Element-wise Operations on Tensors
- Element-wise Multiplication
- torch.matmulT1, T2, out
- Element-wise Division
- Element-wise Addition
- Element-wise Subtraction
- Element-wise Square-root
- Tensor Aggregation
- Tensor In-place operation
- Tensor Logical Operation
- Bitwise or Shift Operations
- Indexing and Slicing in Tensor
- Reshaping Tensors
- Tensor Concatenation
- Tensor Devices CPU or GPU
- GPU in Google Colab
- Memory limitation with Tensors
- Tensor on GPU
- Tensor from CPU to GPU and vice-versa
- Tensor bridge with NumPy
- Recap