What we’re about
This is a group for anyone interested in computer vision.
All skill levels are welcome.
We host free and practical workshops on computer vision with Python.
Upcoming events (3)
See all- Generative AI with Diffusion Models: NVIDIA Certification Workshop for AcademiaLink visible for attendees
https://learn.nvidia.com/courses/course-detail?course_id=course-v1:DLI+C-FX-08+V1
Thanks to improvements in computing power and scientific theory, generative AI is more accessible than ever before. Generative AI plays a significant role across industries due to its numerous applications, such as creative content generation, data augmentation, simulation and planning, anomaly detection, drug discovery, personalized recommendations, and more.
In this course, learners will take a deeper dive into denoising diffusion models, which are a popular choice for text-to-image pipelines.
This course is online and offered free of charge to academic participants (students and staff). If you are in industry, and would like to take the training, please send an email to info@kineto.ai
Important
Access links to the NVIDIA DLI environment required to complete the graded assessment and obtain a certification will be sent to your academic email shortly before the event, please be sure to fill the access form to gain access to it.Learning Objectives
- Build a U-Net to generate images from pure noise
- Improve the quality of generated images with the denoising diffusion process
- Control the image output with context embeddings
- Generate images from English text prompts using the Contrastive Language–Image Pretraining (CLIP) neural network
Topics Covered
- U-Nets
- Diffusion
- CLIP
- Text-to-image Models
From U-net to Diffusion
- Build a U-Net architecture
- Train a model to remove noise from an image
Diffusion Models
- Define the forward diffusion function
- Update the U-Net architecture to accommodate a timestep
- Define a reverse diffusion function
Optimizations
- Implement Group Normalization
- Implement GELU
- Implement Rearrange Pooling
- Implement Sinusoidal Position Embeddings
Classifier-free Diffusion Guidance
- Add categorical embeddings to a U-Net
- Train a model with a Bernoulli mask
CLIP
- Learn how to use CLIP Encodings
- Use CLIP to create a text-to-image neural network
- Fundamentals of Deep Learning: NVIDIA DLI Certification Workshop for AcademiaLink visible for attendees
https://www.nvidia.com/en-eu/training/instructor-led-workshops/fundamentals-of-deep-learning/
Deep Learning with PyTorch Workshop
In this workshop, you’ll learn how deep learning works through hands-on exercises in computer vision and natural language processing. You’ll train deep learning models from scratch, learning tools and tricks to achieve highly accurate results. You’ll also learn to leverage freely available, state-of-the-art pre-trained models to save time and get your deep learning application up and running quickly.
Learning Objectives
By participating in this workshop, you’ll:
- Learn the fundamental techniques and tools required to train a deep learning model
- Gain experience with common deep learning data types and model architectures
- Enhance datasets through data augmentation to improve model accuracy
- Leverage transfer learning between models to achieve efficient results with less data and computation
- Build confidence to take on your own project with a modern deep learning framework
Download workshop datasheet (PDF, 318 KB)
Preparation for the Workshop
- Fill in the form at https://forms.gle/8iNZN3PToUh6iveC9 to gain access codes to the event (will be emailed shortly before it)
- Install Google Chrome or Mozilla Firefox to use the NVIDIA DLI Environment
- Create an account at https://learn.nvidia.com/
Mechanics of Deep Learning
Explore the fundamental mechanics and tools involved in successfully training deep neural networks:- Train your first computer vision model to learn the process of training
- Introduce convolutional neural networks to improve accuracy of predictions in vision applications
- Apply data augmentation to enhance a dataset and improve model generalization
Pre-trained Models
Leverage pre-trained models to solve deep learning challenges quickly. Train recurrent neural networks on sequential data:- Integrate a pre-trained image classification model to create an automatic doggy door
- Leverage transfer learning to create a personalized doggy door that only lets in your dog
Assessment Challenge: Image Classification
Apply computer vision to create a model that distinguishes between fresh and rotten fruit:- Create and train a model that interprets color images
- Build a data generator to make the most out of small datasets
- Improve training speed by combining transfer learning and feature extraction
- Discuss advanced neural network architectures and recent areas of research where students can further improve their skills
Final Review
- Review key learnings and answer questions
- Complete the assessment and earn a certificate
- Complete the workshop survey
- Learn how to set up your own AI application development environment
