If you are building a robot driven by Raspberry Pi and want to use image recognition and object detection you may want to look into Googles Mobile Nets platform which lets you do use a several mobile-first computer vision models for TensorFlow, combined with an Intel Movidius Neural Compute Stick on a Rasrberry PI 3. The MobileNets platform is designed to be run on resource conservative devices while maintaining accuracy and the latter will give you an order of magnitude more compute power than running the detection on the raspberrys CPU.
The fourth course, Convolutional Neural Networks of Deeplearning.ai has now been released on coursera. People have been waiting for this one, but i think that the delay was to make the material very up to date with current research results. The four weeks of learning deals with:
- Foundations of Convolutional Neural Networks
- Deep convolutional models: case studies
- Object detection
- Special applications: Face recognition & Neural style transfer
The “YOLO9000: Better, Faster, Stronger” paper describes the improvements to the YOLO, You only look once, architecture that enables realtime object detection and classification. It can classify over 9000 object categories and outperforms Faster RCNN with ResNet and SSD while being significantly faster. They train on both COCO dataset for detection simultaneously with ImageNet for Classification and combine it with a wordtree so that they can also fallback to “dog” if they cannot classify for instance a specific dog breed.
The first version, and architecture can be seen in this paper.
Here is a video presentation: https://www.youtube.com/watch?v=GBu2jofRJtk
The video lectures for Stanfords very popular CS231n (Convolutional Neural Networks for Visual Recognition) that was held in Spring 2017 was released this month. (According to their twitter page, the cs231n website gets over 10 000 views per day. The reading material on their page is really good at explaining CNNs)
Here are the video lectures:
- Lecture 1 | Introduction to Convolutional Neural Networks for Visual Recognition
- Lecture 2 | Image Classification
- Lecture 3 | Loss Functions and Optimization
- Lecture 4 | Introduction to Neural Networks
- Lecture 5 | Convolutional Neural Networks
- Lecture 6 | Training Neural Networks I
- Lecture 7 | Training Neural Networks II
- Lecture 8 | Deep Learning Software
- Lecture 9 | CNN Architectures
- Lecture 10 | Recurrent Neural Networks
- Lecture 11 | Detection and Segmentation
- Lecture 12 | Visualizing and Understanding
- Lecture 13 | Generative Models
- Lecture 14 | Deep Reinforcement Learning
- Lecture 15 | Efficient Methods and Hardware for Deep Learning
- Lecture 16 | Adversarial Examples and Adversarial Training
These are the assignments for the course:
- Assignment #1: Image Classification, kNN, SVM, Softmax, Neural Network
- Assignment #2: Fully-Connected Nets, Batch Normalization, Dropout, Convolutional Nets
- Assignment #3: Image Captioning with Vanilla RNNs, Image Captioning with LSTMs, Network Visualization, Style Transfer, Generative Adversarial Networks
Also Make sure to check out last years student reports. note: one is about improving the state of the art of detecting the Higgs Boson.
The course page is here: http://cs231n.stanford.edu/