Share

Deep Learning Workshop : Applied Computer Vision

DESCRIPTION   Deep Learning Workshop : Applied Computer Vision  This practical workshop will focus on using deep learning for applied computer vision tasks. We will present different families of models (CNNs, Vision Transformers), how they work and how to train them. Both theory and practical implementations will be covered. After this course, participants will have the basic knowledge to implement their own computer vision models, as well as understand best practices for training, fine-tuning and selecting models, as well as monitoring experiments. TARGETED AUDIENCE Industry professionals looking to learn more about applied computer vision and deep learning ML Engineer/Scientist Applied Research Scientist AI/ML Technical Lead AI Solutions Architect  Academics Students (Bachelors, MSc., PhD) with an interest in deep learning Enthusiasts curious to learn about deep learning and computer vision SESSIONS   Session 1 - Introduction to image classification - theory Tuesday, October 4, 2022 Duration: 2 hours Review images are and how computers interpret them (grayscale vs. RGB images) Review of concepts behind image classification in a supervised learning setting Common neural network architectures and their underlying operations (Multilayer perceptrons, Convolutional neural networks) Gradient descent intuitions and the role of the learning rate and optimizer How to evaluate models, performance metrics, confusion matrices, precision, recall, etc. Session 2 -  Introduction to image classification - practical Friday, October 7, 2022 Duration: 2 hours Summary: This will be a hands-on, live-coding session The task will be to implement a rock, paper, scissors game using pytorch Simple models will be implemented and trained from scratch (e.g. MLP, LeNet) Training loops and evaluation routines will be implemented Data splits will be considered, as well as concepts behind data augmentation and data distribution shifts Session 3 -DL Models, training and finetuning - theory Tuesday, October 11, 2022 Duration: 2 hours Overview of the evolution of state-of-the-art models on the ImageNet benchmark (VGG, ResNet) Introduction to self-attention, transformers and vision transformers (ViT) Comparisons (pros, cons, differences) between CNNs and ViT (Tradeoffs, benchmarks, speed, inference, model size etc.) Introduction to foundation models and applications (e.g. CLIP) Introduction to object detection and image segmentation Session 4 - Implementation of a DL project - practical Duration: 2 hours Friday, October 14, 2022 Summary: In this session, We will be implementing a remote-sensing task on the bigearthnet dataset (multi-label classification). We will implement a baseline and compare it to state-of-the-art models (both pre-trained and fine-tuned and trained from scratch). Concepts of fine-tuning pretrained models and hyper parameter tuning will be explained and implemented. Focus will be on what goes into implementing the codebase for larger models/datasets as well as best practices surrounding the experiments - debugging, monitoring results, testing, reporting, checkpointing etc. TRAINERS Jeremy Pinto    Senior Applied Research Scientist LinkedIn     WORKSHOP TRAINING Duration : 8 hours - over 2 weeks - ONLINE   Level: Intermediate to advanced  Language:  English October 4th -14th 2022 4 sessions - e very Tuesday and Friday 9:00 AM to 11:00 AM (EDT, UTC-4) TRAINING CERTIFIED BY SCALE AI 50% discount on General Admission for Canadians and professionals working in Canada Promo Code: IVA_Scale_DLW0922 LEARNING OBJECTIVES Apply deep learning to image classification tasks Prepare and process images to pass them through deep learning models  Examine and compare the characteristics of the main deep learning vision algorithms (e.g., Convolutional Neural Networks, Vision Transformers) and pretrained models (e.g., ResNets, ViTs) Train a model using best practices (e.g., experiment management, code versioning, model checkpointing, etc.) Properly evaluate the performance of the models (e.g., accuracy, F1 score, confusion matrix, etc.) PREREQUISITES Basic linear algebra concepts (matrix multiplication, vector dot product, etc.)  Background in Machine Learning is recommended but not strictly necessary (supervised learning, gradient descent and backpropagation)  Basic programming (working knowledge of Python or similar language) is strongly recommended for the tutorials REGISTRATION FEES*** General Admission  600$ + tx** Student*  100$ + tx** *On presentation of a university ID. (Send it to formations@ivado.ca ) ** Prices are in Canadian dollars, and local taxes (GST, QST) are only applicable for Canadian participants. *** SCALE AI Discount is only applicable to Canadian citizens and / or people working in Canada. For other participants, general admission applies. Registration ends on Friday, September 30, 2022 ADDITIONAL INFORMATION Attestation For the delivery of a certificate for a successful completion to this online workshop, participants must attend the live sessions on a weekly basis. Note to IVADO members  If as an industrial member you have received a member promo code, and, as you are also eligible to Scale AI as a working individual, you may combine both promo codes upon general admission registration.  Check with your manager for promotional codes before registering.  Please note that promo codes are non-transferable and non-exchangeable ASSISTANCE AND SUPPORT For information on programming:  formations@ivado.ca