Want to stay in shape with your deep learning skills? Let’s lift some tensors, and learn (or revise) together useful and important skills or concepts when building deep learning models in TensorFlow or PyTorch. The posts below are heavily inspired from the amazing series of videos from Andrej Karpathy on neural network.

• 
  Deep Learning Gymnastics #1: Tensor Broadcasting
  Master broadcasting like a pro and learn how a single trick can make your deep learning code faster, cleaner, and more elegant.
• 
  Deep Learning Gymnastics #2: Tensor Indexing
  Learn how smart indexing lets you build batches, embeddings, and masked ops efficiently in modern DL frameworks.
• 
  Deep Learning Gymnastics #3: Tensor (re)Shaping
  Your tensors aren’t the right shape? Learn how to reshape, squeeze, and stack them like a deep learning gymnast.
• 
  Deep Learning Gymnastics #4: Master Your (LLM) Cross Entropy
  Use all the gymnastics tricks we’ve learned in order to master (LLM) cross-entropy in PyTorch and TensorFlow.