Modern CV Models
Use YOLO, SAM, ViT, and other modern CV architectures.
0%
Confidence · no data yet
After this skill you can…
- Run YOLO for real-time object detection
- Use SAM for zero-shot segmentation
- Fine-tune ViT on custom datasets
Prerequisites
Watch (10 videos)
YOLOE: Real-time Zero-shot Object Detection | Visual Prompting | Live Coding & Q&A (Mar 14th)
→ Implement YOLOE for real-time object detection→ Use visual prompting for zero-shot learning
RF-DETR: How to Train SOTA for Object Detection on a Custom Dataset | Step-by-step guide
→ Train an object detection model→ Deploy a custom model
Mesh Optimization Using FlexiCubes with NVIDIA Kaolin Library v0.15.0
→ Optimize meshes using FlexiCubes→ Apply gradient-based optimization to scalar fields
Code Panoptic Image Segmentation w/ Vision Transformer & Mask2Former - A PyTorch tutorial
→ Implement instance segmentation with Mask2Former→ Build semantic segmentation models with Vision Transformer
Implementing DietNeRF with JAX and Flax
→ Implement DietNeRF for neural rendering→ Reconstruct 3D scenes with NeRF
Image Classification with Keras: Build & Optimize
→ Build image classification models with Keras→ Apply transfer learning to CNNs→ Optimize model performance with image augmentation
Test-time Adaptable Neural Networks for Robust Medical Image Segmentation | JRC Workshop 2021
→ Implement a test-time adaptable neural network for image segmentation→ Train a CNN for medical image analysis
Vision Models: Train and Evaluate
→ Train a CNN model for image classification→ Evaluate the performance of a Vision Transformer model
Florence-2: Create and Deploy a Custom Vision Language Model
→ Create custom vision language models→ Deploy models with Roboflow
Open Source Computer Vision Deployment with Roboflow Inference
→ Deploy a computer vision model to production→ Create a standardized API for computer vision models
DeepCamp AI