![ConvNets
32
32
3
Convolution Layer
activation maps
6
28
For example, if we had 6 5x5 filters, we’ll get 6 separate activation maps:
We processed [32x32x3] volume into [28x28x6] volume.
Q: how many parameters are used ?
A: (5*5*3)*6 = 450 parameters, (5*5*3)*(28*28*6) = ~350K multiplies
28](https://image.slidesharecdn.com/dl-hubba-01-170226085713/85/Hubba-Deep-Learning-11-320.jpg)
Hubba Deep Learning
- 1. Deep Learning meetup Protobuf/Lua (Caffe/Torch) Python (TensorFlow) Java (DeepLearning4J)
- 3. AI Landscape
- 4. Stage of AI
- 6. What is (not) DL ● Deep Learning is not GOFAI ● Deep Learning is different than ML ● Deep Learning doesn't mimic Brain ● Deep Learning is not Statistics ● Deep Learning is not Big Data ● Deep Learning is not made by Data Scientists ● Deep Learning is not ANN or MLP
- 10. ConvNets 32 32 3 Convolution Layer 32x32x3 image 5x5x3 filter convolve (slide) over all spatial locations activation map 1 28 28
- 11. ConvNets 32 32 3 Convolution Layer activation maps 6 28 For example, if we had 6 5x5 filters, we’ll get 6 separate activation maps: We processed [32x32x3] volume into [28x28x6] volume. Q: how many parameters are used ? A: (5*5*3)*6 = 450 parameters, (5*5*3)*(28*28*6) = ~350K multiplies 28
- 13. ● InputLayer ● ConvLayer ● ReLuLayer ● PoolLayer ● FullyConnLayer ● SoftMaxLayer
- 14. Models ● LeNet - 1998 ● AlexNet - ILSVRC 2012 ● ZFNet - ILSVRC 2013 ● GoogLeNet - ILSVRC 2014 ● VGGNet - ILSVRC 2014 ● ResNet - ILSVRC 2015 ● ILSVRC 2016
- 16. Karpathy ● Matlab is so 2012 ● Caffe is so 2013 ● Theano is so 2014 ● Torch is so 2015 ● TensorFlow is so 2016 ● *PyTorch is so 2017
- 17. Links ● DL4J-examples ● Deep Learning Papers ● ConvNetJava ● NVIDIA DIGITS ● Darknet ● Awesome Deep Learning Papers ● Learning for Self-Driving Cars
- 18. Links v2 ● Graphcore Poplar ● Dlib ● Udacity's Self-Driving Car Simulator ● DL4J Model Zoo ● Trained models for Keras ● DIGITS Object Detection ● DIGITS Semantic Segmentation
- 19. Data to train ● Auto Pilot ● Traffic Light Recognition ● Traffic Signs Recognition ● Lane Finding ● Object Recognition
- 20. Autonomous car ● Autopilot TensorFlow ● Udacity self-driving car ● CommaAI openpilot ● FUBAR Labs ● Nvidia Autopilot Keras GTA V ● Udacity self-driving car nanodegree ● Traffic Light Recognition ● Traffic Signs Recognition ● Quadcopter Navigation