hoangcuong2011

PyTorch to MXNet

This cheatsheet serves as a quick reference for PyTorch users who are interested in trying MXNet, and vice versa.

Pytorch is a deep learning framework provides imperative tensor manipulation and neural network training. MXNet provides similar imperative tensor manipulation through the ndarray package and neural network training through gluon. This cheatsheet maps functions one-by-one between these two frameworks.

Note that MXNet has a symbolic interface similar to Keras and Tensorflow that may provide better performance and portability. This cheatsheet mainly focus on MXNet's imperative interface.

Installation

hoangcuong2011

hoangcuong2011

import numpy as np
from keras.callbacks import LearningRateScheduler

def step_decay_schedule(initial_lr=1e-3, decay_factor=0.75, step_size=10):
    '''
    Wrapper function to create a LearningRateScheduler with step decay schedule.
    '''
    def schedule(epoch):
        return initial_lr * (decay_factor ** np.floor(epoch/step_size))
    

hoangcuong2011

''' Script for downloading all GLUE data.

Note: for legal reasons, we are unable to host MRPC.
You can either use the version hosted by the SentEval team, which is already tokenized, 
or you can download the original data from (https://download.microsoft.com/download/D/4/6/D46FF87A-F6B9-4252-AA8B-3604ED519838/MSRParaphraseCorpus.msi) and extract the data from it manually.
For Windows users, you can run the .msi file. For Mac and Linux users, consider an external library such as 'cabextract' (see below for an example).
You should then rename and place specific files in a folder (see below for an example).

mkdir MRPC
cabextract MSRParaphraseCorpus.msi -d MRPC

hoangcuong2011

# Author: Kyle Kastner
# License: BSD 3-Clause
# Implementing http://mnemstudio.org/path-finding-q-learning-tutorial.htm
# Q-learning formula from http://sarvagyavaish.github.io/FlappyBirdRL/
# Visualization based on code from Gael Varoquaux gael.varoquaux@normalesup.org
# http://scikit-learn.org/stable/auto_examples/applications/plot_stock_market.html

import numpy as np
import matplotlib.pyplot as plt
from matplotlib.collections import LineCollection

hoangcuong2011

Code for Keras plays catch blog post

Train

python qlearn.py

Test

1. Generate figures

hoangcuong2011

# Example for my blog post at:
# https://danijar.com/introduction-to-recurrent-networks-in-tensorflow/
import functools
import sets
import tensorflow as tf


def lazy_property(function):
    attribute = '_' + function.__name__

hoangcuong2011

# Example for my blog post at:
# http://danijar.com/introduction-to-recurrent-networks-in-tensorflow/
import functools
import sets
import tensorflow as tf


def lazy_property(function):
    attribute = '_' + function.__name__