What is pytorch?

Create torch tensors

import PyTorcha = PyTorch.FloatTensor(2,3).uniform()a += 3print('a', a)print('a.sum()', a.sum())

Instantiate nn network modules

import PyTorchfrom PyTorchAug import nnnet = nn.Sequential()net.add(nn.SpatialConvolutionMM(1, 16, 5, 5, 1, 1, 2, 2))net.add(nn.ReLU())net.add(nn.SpatialMaxPooling(3, 3, 3, 3))net.add(nn.SpatialConvolutionMM(16, 32, 3, 3, 1, 1, 1, 1))net.add(nn.ReLU())net.add(nn.SpatialMaxPooling(2, 2, 2, 2))net.add(nn.Reshape(32 * 4 * 4))net.add(nn.Linear(32 * 4 * 4, 150))net.add(nn.Tanh())net.add(nn.Linear(150, 10))net.add(nn.LogSoftMax())net.float()crit = nn.ClassNLLCriterion()crit.float()net.zeroGradParameters()input = PyTorch.FloatTensor(5, 1, 28, 28).uniform()labels = PyTorch.ByteTensor(5).geometric(0.9).icmin(10)output = net.forward(input)loss = crit.forward(output, labels)gradOutput = crit.backward(output, labels)gradInput = net.backward(input, gradOutput)net.updateParameters(0.02)

Write your own lua class, call methods on it

require 'torch'require 'nn'local TorchModel = torch.class('TorchModel')function TorchModel:__init(backend, imageSize, numClasses)  self:buildModel(backend, imageSize, numClasses)  self.imageSize = imageSize  self.numClasses = numClasses  self.backend = backendendfunction TorchModel:buildModel(backend, imageSize, numClasses)  self.net = nn.Sequential()  local net = self.net  net:add(nn.SpatialConvolutionMM(1, 16, 5, 5, 1, 1, 2, 2))  net:add(nn.ReLU())  net:add(nn.SpatialMaxPooling(3, 3, 3, 3))  net:add(nn.SpatialConvolutionMM(16, 32, 3, 3, 1, 1, 1, 1))  net:add(nn.ReLU())  net:add(nn.SpatialMaxPooling(2, 2, 2, 2))  net:add(nn.Reshape(32 * 4 * 4))  net:add(nn.Linear(32 * 4 * 4, 150))  net:add(nn.Tanh())  net:add(nn.Linear(150, numClasses))  net:add(nn.LogSoftMax())  self.crit = nn.ClassNLLCriterion()  self.net:float()  self.crit:float()endfunction TorchModel:trainBatch(learningRate, input, labels)  self.net:zeroGradParameters()  local output = self.net:forward(input)  local loss = self.crit:forward(output, labels)  local gradOutput = self.crit:backward(output, labels)  self.net:backward(input, gradOutput)  self.net:updateParameters(learningRate)  local _, prediction = output:max(2)  local numRight = labels:int():eq(prediction:int()):sum()  return {loss=loss, numRight=numRight}  -- you can return a table, it will become a python dictionaryendfunction TorchModel:predict(input)  local output = self.net:forward(input)  local _, prediction = output:max(2)  return prediction:byte()end

import PyTorchimport PyTorchHelpersimport numpy as npfrom mnist import MNISTbatchSize = 32numEpochs = 2learningRate = 0.02TorchModel = PyTorchHelpers.load_lua_class('torch_model.lua', 'TorchModel')torchModel = TorchModel(backend, 28, 10)mndata = MNIST('../../data/mnist')imagesList, labelsList = mndata.load_training()labels = np.array(labelsList, dtype=np.uint8)images = np.array(imagesList, dtype=np.float32)labels += 1  # since torch/lua labels are 1-basedN = labels.shape[0]numBatches = N // batchSizefor epoch in range(numEpochs):  epochLoss = 0  epochNumRight = 0  for b in range(numBatches):    res = torchModel.trainBatch(      learningRate,      images[b * batchSize:(b+1) * batchSize],      labels[b * batchSize:(b+1) * batchSize])    numRight = res['numRight']    epochNumRight += numRight  print('epoch ' + str(epoch) + ' accuracy: ' + str(epochNumRight * 100.0 / N) + '%')

Installation

Pre-requisites

luarocks install nn

pip install -r requirements.txt

pip install -r test/requirements.txt

Procedure

git clone https://github.com/hughperkins/pytorch.gitcd pytorchsource ~/torch/install/bin/torch-activate./build.sh

Unit-tests

source ~/torch/install/bin/torch-activatecd pytorch./run_tests.sh

Python 2 vs Python 3?

Maintainer guidelines

Versioning

Related projects

Support?

Recent news