GalaxyKickStart is an Ansible playbook designed to help you get one or more production-ready Galaxy servers based on Ubuntu within minutes, and to maintain these servers. Optionally, instances can be pre-loaded with tools and workflows. Detailed usage instructions are available in the Documentation.
Aim to visualize the final fully-connected layer's hidden units This is an implemetation of Visualizing higher-layer features of a deep network find the optimal stimulus for each unit by performing gradient descent in image space to maximize the units activation See Visualization-of-VGG19.ipynb for the codes and results
#Feature Visualization for Convnets in Tensorflow This is the code to accompany a post on Visualizing Features from a Convolutional Network. ##Instructions for running: Download the cifar10 binary format, place into /cifar-10-batches-py directory run main.py run conv.py to compile many image files into the group ones shown in the post
Visualizing parts of Convolutional Neural Networks using Keras and Cats This repo contains a notebook with code for visualizing CNNs using cats. Requirements: Keras numpy opencv (although it is only used for opening an image, you can use anything that can open an image as a numpy ndarray) matplotlib
Pytorch Viewer(模型可视化工具) 实现以下可视化 1.saliency map. ref:https://arxiv.org/pdf/1312.6034.pdf 2.feature map. 3.feature map back mapping. ref:https://www.cs.nyu.edu/~fergus/papers/zeilerECCV2014.pdf
Tensorboard-own-image-data-image-features-embedding-visualization Learn how to visualize your own image data or features on Tensorboard Embedding Visualizer. The video tutorial for the same is available at: https://www.youtube.com/watch?v=CNR7Wu7g2aY
Easy-deep-learning-with-Keras If you are unfamiliar with data preprocessing, first review NumPy & Pandas sections of Python for data analysis materials. Materials in this repository are for educational purposes. Source code is written in Python 3.6+ & Keras ver 2.0+ (Using TensorFlow backend - For advanced topics, basic understanding of TensorFlow mechanics is necessary) 1. Multilayer Perceptrons 1) Basics of MLP Regression tasks with MLP Classification tasks with MLP 2) Advanced MLP
Github 加载 .ipynb 的速度较慢，建议在 Nbviewer 中查看该项目。 简介 大部分内容来自keras项目中的examples 目录 01.多层感知机实现 02.模型的保存 03.模型的加载 04.绘制精度和损失曲线 05.卷积神经网络实现 06.CIFAR10_cnn 07.mnist_lstm 08.VGG16调用 09.卷积滤波器可视化 10.variational_autoencoder 11.锁定层fine-tuning网络 12.使用sklearn wrapper进行的参数搜索 13.Keras和Tensorflow联合使用 14.Finetune InceptionV3样例 15.自编码器 16.卷积自编码器
Simple tutorials on deep learning using TensorFlow Eager This repo aims to help people who would like to start getting hands-on experience with deep learning using the TensorFlow Eager mode. TensorFlow Eager mode lets you build neural networks as easy as you would do with Numpy, with the huge advantage that it provides automatic differentiation (no more handwritten backprop. YAAAY!). It can ran also on GPUs making the neural networks training significantly faster. I will try to make the tutori
keras-vis is a high-level toolkit for visualizing and debugging your trained keras neural net models. Currently supported visualizations include: Activation maximization Saliency maps Class activation maps All visualizations by default support N-dimensional image inputs. i.e., it generalizes to N-dim image inputs to your model. The toolkit generalizes all of the above as energy minimization problems with a clean, easy to use, and extendable interface. Compatible with both theano a
cheatsheets-ai Essential Cheat Sheets for deep learning and machine learning researchers Tensorflow Keras Neural Networks Zoo Numpy Scipy Pandas-1 Pandas-2 Pandas-3 Scikit-learn Matplotlib ggplot2-1 ggplot2-2 PySpark PySpark-RDD PySpark-SQL R Studio(dplyr & tidyr)-1 R Studio(dplyr & tidyr)-2 Neural Network Cells Neural Network Graphs Deep Learning Cheat Sheet All Cheat Sheets(PDF) https://medium.com/@kailashah
