.. image:: pyeco.png :height: 20 :alt: Economie :target: http://www.xavierdupre.fr/app/ensae_teaching_cs/helpsphinx/td_2a_notions.html#pour-un-profil-plutot-economiste .. image:: pystat.png :height: 20 :alt: Statistique :target: http://www.xavierdupre.fr/app/ensae_teaching_cs/helpsphinx/td_2a_notions.html#pour-un-profil-plutot-data-scientist Classification d'images +++++++++++++++++++++++ (*à venir*) *Lectures* * `VGG Convolutional Neural Networks Practical `_ * `Image-to-Image Translation with Conditional Adversarial Networks `_, `Image to Image demo `_ * `Image-to-Image Translation with Conditional Adversarial Networks `_ * `How to Train a GAN? Tips and tricks to make GANs work `_ * `Towards Principled Methods for Training Generative Adversarial Networks `_ * `Instance Noise: A trick for stabilising GAN training `_ * `Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network `_ * `YOLO9000: Better, Faster, Stronger `_ : détection en temps d'objets sur des images ou dans une vidéo, le code est sur github `darknet `_, wrapper Python : `darknetpy `_, `demo `_ * `SSD: Single Shot MultiBox Detector `_ (voir aussi `caffe/ssd `_) * `HPatches: A benchmark and evaluation of handcrafted and learned local descriptors `_ * `Learning Transferable Architectures for Scalable Image Recognition `_ *Algorithmes* * `Viola–Jones object detection framework `_ * `Histograms of Oriented Gradients for Human Detection (HOG) `_ * `One Millisecond Face Alignment with an Ensemble of Regression Trees `_, `Github/AndrejMaris/facefit `_ * `ageitgey/step-2a_finding-face-landmarks.py `_ *Outils* * `Image Descriptors `_, `Speeded up robust features (SURF) `_, `Scale-invariant feature transform (SIFT) `_, *Modules* * `VIGRA `_ * `opencv `_ * `dlib `_ * `hed `_ (Holistically-Nested Edge Detection) * `bob.bio `_ * tous les modules de :ref:`l-deep-learning` * `plat `_ (Utilities for exploring generative latent spaces as described in the `Sampling Generative Networks `_ paper.) * `darknetpy `_ *Modèles pré-entraînés* * `VGG16 model for Keras `_, `VGG in TensorFlow `_, `Very Deep Convolutional Networks for Large-Scale Visual Recognition `_