After revolutionizing many scientific fields, artificial intelligence is now taking root in industry. In practice, it is supported by Python frameworks such as PyTorch, now a leader in deep learning.

Technical resources

Course material projected during training and sent to all trainees at the end of the course; case studies and practical examples chosen according to trainees' areas of interest

Performance monitoring

All trainees are asked to sign in every half-day Evaluation: Questionnaire to assess skills acquired at the end of the course

Assessment of results

Post-training satisfaction questionnaire

Pedagogical objectives

By way of example, participants are led to understand the key concepts of these technologies and the latest developments.

Technologies covered

Tensor, autograd, torch.nn, Module, torch.optim, tensorboard, torchvision examples, TorchScript, torch.hub, torch.utils.dat

Target skills

  • Applied introduction to deep learning
  • From numpy to PyTorch: ndarray, Tensor, autograd, optimization
  • Data pipelines: Datasets, Extract-Transform-Load, epoch, batch, custom datasets, iterable
    datasets
  • torch.nn: Model definition, learning, checkpointing, inference
  • Custom modules: autograd functions, new modules, new layers, debugging
  • PyTorch models in production: Flask & REST API, TorchScript, ONNX