BigSnarf blog

Infosec FTW

3 Pillars of Autonomous Driving

T-SNE attack data

VAE Tensorflow

Faster R-CNN Pedestrian and Car Detection

pedesterian_detection

Code https://github.com/bigsnarfdude/Faster-RCNN_TF

Faster RCNN for Pedestrian Detection https://arxiv.org/pdf/1607.07032v2.pdf

Tutorial http://kaiminghe.com/icml16tutorial/index.html

http://techtalks.tv/talks/deep-residual-networks-deep-learning-gets-way-deeper/62358/

Faster RCNN original https://arxiv.org/pdf/1506.01497v3.pdf

Slides ILSCVRC 2015 http://image-net.org/challenges/talks/ilsvrc2015_deep_residual_learning_kaiminghe.pdf

Fast RCNN original https://arxiv.org/pdf/1504.08083v2.pdf

RCNN original https://people.eecs.berkeley.edu/~rbg/papers/pami/rcnn_pami.pdf

SPP-Net paper https://arxiv.org/pdf/1406.4729v4.pdf

screen-shot-2016-11-19-at-8-11-24-am

Keras Cats and Dogs

Create Validation Dataset

THEANO_FLAGS=device=gpu,floatX=float32 python script_1.py

THEANO_FLAGS=device=gpu,floatX=float32 python script_2.py

https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html

https://github.com/openimages/dataset/wiki/Running-a-pretrained-classifier

Visualizing Convnet Layers and activations

Raw data in jpeg format

seveb

jpeg converted to greyscale value integers in numpy array

screen-shot-2016-10-19-at-1-13-44-pm

integers converted to floats in numpy array

screen-shot-2016-10-19-at-1-13-34-pm

floats are between values 0.0-255.0 need to be converted to floats between 0.0-1.0

screen-shot-2016-10-19-at-1-13-21-pm

These are visualizations of the filters in Tensorflow layers

screen-shot-2016-10-18-at-5-06-38-pm

These are the visualization of the activations of the Tensorflow convolutional layers

screen-shot-2016-10-18-at-1-33-32-pm

Self Driving Car Standards

Testing (Semi) Autonomous Cars With Tesla, Cadillac, Hyundai, and Mercedes

Tesla Autopilot is shown outperforming Mercedes, Hyundai and Cadillac in third-party tests

Tesla is about to increase its lead in semi-autonomous driving w/ ‘Tesla Vision’: computer vision based on NVIDIA’s parallel computing

 

definition programmer

cthl-m9wcaeub1y

Steps to deep learning

screen-shot-2016-09-29-at-10-40-44-am

  1. Clean Dataset
  2. Choose an appropriate model
  3. Choose an activation function
  4. Choose a cost function
  5. Iterate to Optimize

GPS RTK