All Projects → jvns → Neural Nets Are Weird

jvns / Neural Nets Are Weird

Projects that are alternatives of or similar to Neural Nets Are Weird

Deeplearning
Stars: ✭ 161 (-0.62%)
Mutual labels:  jupyter-notebook
Contrastivelosses4vrd
Implementation for the CVPR2019 paper "Graphical Contrastive Losses for Scene Graph Generation"
Stars: ✭ 162 (+0%)
Mutual labels:  jupyter-notebook
Feature Engineering Made Easy
Feature Engineering Made Easy, published by Packt
Stars: ✭ 162 (+0%)
Mutual labels:  jupyter-notebook
Hitchhikers Guide Machine Learning
Guide explaining and implementing fundamental machine learning algorithms in Python
Stars: ✭ 161 (-0.62%)
Mutual labels:  jupyter-notebook
Covid
Tracking Coronavirus Growth
Stars: ✭ 162 (+0%)
Mutual labels:  jupyter-notebook
Real Time Facial Expression Recognition
A Deep Learning Case Study to detect one of the Seven Human Facial Expressions in Still Images and in Real Time. This model is also trained enough to Detect Facial Expressions of Animated Images.
Stars: ✭ 162 (+0%)
Mutual labels:  jupyter-notebook
Uq Course
Introduction to Uncertainty Quantification
Stars: ✭ 161 (-0.62%)
Mutual labels:  jupyter-notebook
Image keras
Building an image classifier using keras
Stars: ✭ 162 (+0%)
Mutual labels:  jupyter-notebook
Dd Net
A lightweight network for body/hand action recognition
Stars: ✭ 161 (-0.62%)
Mutual labels:  jupyter-notebook
Cs231n
My assignment solutions for CS231n - Convolutional Neural Networks for Visual Recognition
Stars: ✭ 162 (+0%)
Mutual labels:  jupyter-notebook
Machine learning
Estudo e implementação dos principais algoritmos de Machine Learning em Jupyter Notebooks.
Stars: ✭ 161 (-0.62%)
Mutual labels:  jupyter-notebook
Lolita
Using github's issue system as lightweight notes & blog.
Stars: ✭ 161 (-0.62%)
Mutual labels:  jupyter-notebook
Pythonfromdatods
图书《Python编程:从数据分析到数据科学》的配套资源
Stars: ✭ 162 (+0%)
Mutual labels:  jupyter-notebook
Merf
Mixed Effects Random Forest
Stars: ✭ 161 (-0.62%)
Mutual labels:  jupyter-notebook
Load forecasting
Load forcasting on Delhi area electric power load using ARIMA, RNN, LSTM and GRU models
Stars: ✭ 160 (-1.23%)
Mutual labels:  jupyter-notebook
Far Ho
Gradient based hyperparameter optimization & meta-learning package for TensorFlow
Stars: ✭ 161 (-0.62%)
Mutual labels:  jupyter-notebook
Visualizing Cnn Feature Maps
Visualizing CNN filters using PyTorch
Stars: ✭ 162 (+0%)
Mutual labels:  jupyter-notebook
Sas kernel
A Jupyter kernel for SAS. This opens up all the data manipulation and analytics capabilities of your SAS system within a notebook interface. Use the Jupyter Notebook interface to execute SAS code and view results inline.
Stars: ✭ 162 (+0%)
Mutual labels:  jupyter-notebook
Pix2pix Film
An implementation of Pix2Pix in Tensorflow for use with frames from films
Stars: ✭ 162 (+0%)
Mutual labels:  jupyter-notebook
Pytket
Python module for interfacing with the CQC t|ket> library of quantum software
Stars: ✭ 162 (+0%)
Mutual labels:  jupyter-notebook

neural nets are weird

Source code for the article How to trick a neural network into thinking a panda is a vulture. Here's how to get it going! It will download about 1.5GB and take maybe half an hour to set up and compile everything, so don't expect it to be instant. Tested on Linux and OS X.

git clone https://github.com/jvns/neural-nets-are-weird
cd neural-nets-are-weird
make image
make notebook

On Linux: Once you've run those commands, open http://localhost:9990/notebooks/notebooks/neural-nets-are-weird.ipynb?token=weirdness and you should be good to go! This starts an IPython Notebook server, which lets you run code interactively.

On OSX: You must use the address of the VM hosting Docker in the URL (not localhost). This address is shown when starting Docker, or you can get the docker-address by running the command docker-machine ip default Then point your browser to http://docker-address:9990 and follow along with the instructions in the IPython notebook.

There's another Docker image for Caffe here

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].