2016-08-15 111 views
1

我有一個Lusty(OpenResty的框架)API,它包裝了一個Torch分類器。到目前爲止,我已經能夠得到一個單一的請求工作,但是到API每個後續請求觸發以下錯誤,沒有詳細的堆棧跟蹤:Lua Torch7&OpenResty:試圖索引一個零值

attempt to index a nil value 

出現的錯誤,當我打電話給拋出:

net:add(SpatialConvolution(3, 96, 7, 7, 2, 2)) 

成功完成第一個請求而每個附加請求失敗的行爲是解決問題的線索。

我已將以下完整代碼粘貼到app/requests/classify.lua。這似乎是某種變量緩存/初始化問題,雖然我對Lua的有限知識不能幫助我調試問題。我已經嘗試過做很多事情,包括將我的導入改爲local torch = require('torch')等本地化變量,並將這些導入移到classifyImage()函數中。

torch = require 'torch' 
nn = require 'nn' 
image = require 'image' 
ParamBank = require 'ParamBank' 
label  = require 'classifier_label' 
torch.setdefaulttensortype('torch.FloatTensor') 

function classifyImage() 

    local opt = { 
    inplace = false, 
    network = "big", 
    backend = "nn", 
    save = "model.t7", 
    img = context.input.image, 
    spatial = false, 
    threads = 4 
    } 
    torch.setnumthreads(opt.threads) 

    require(opt.backend) 
    local SpatialConvolution = nn.SpatialConvolutionMM 
    local SpatialMaxPooling = nn.SpatialMaxPooling 
    local ReLU = nn.ReLU 
    local SpatialSoftMax = nn.SpatialSoftMax 

    local net = nn.Sequential() 

    print('==> init a big overfeat network') 
    net:add(SpatialConvolution(3, 96, 7, 7, 2, 2)) 
    net:add(ReLU(opt.inplace)) 
    net:add(SpatialMaxPooling(3, 3, 3, 3)) 
    net:add(SpatialConvolution(96, 256, 7, 7, 1, 1)) 
    net:add(ReLU(opt.inplace)) 
    net:add(SpatialMaxPooling(2, 2, 2, 2)) 
    net:add(SpatialConvolution(256, 512, 3, 3, 1, 1, 1, 1)) 
    net:add(ReLU(opt.inplace)) 
    net:add(SpatialConvolution(512, 512, 3, 3, 1, 1, 1, 1)) 
    net:add(ReLU(opt.inplace)) 
    net:add(SpatialConvolution(512, 1024, 3, 3, 1, 1, 1, 1)) 
    net:add(ReLU(opt.inplace)) 
    net:add(SpatialConvolution(1024, 1024, 3, 3, 1, 1, 1, 1)) 
    net:add(ReLU(opt.inplace)) 
    net:add(SpatialMaxPooling(3, 3, 3, 3)) 
    net:add(SpatialConvolution(1024, 4096, 5, 5, 1, 1)) 
    net:add(ReLU(opt.inplace)) 
    net:add(SpatialConvolution(4096, 4096, 1, 1, 1, 1)) 
    net:add(ReLU(opt.inplace)) 
    net:add(SpatialConvolution(4096, 1000, 1, 1, 1, 1)) 
    net:add(nn.View(1000)) 
    net:add(SpatialSoftMax()) 
    -- print(net) 

    -- init file pointer 
    print('==> overwrite network parameters with pre-trained weigts') 
    ParamBank:init("net_weight_1") 
    ParamBank:read(  0, {96,3,7,7},  net:get(1).weight) 
    ParamBank:read( 14112, {96},   net:get(1).bias) 
    ParamBank:read( 14208, {256,96,7,7}, net:get(4).weight) 
    ParamBank:read( 1218432, {256},   net:get(4).bias) 
    ParamBank:read( 1218688, {512,256,3,3}, net:get(7).weight) 
    ParamBank:read( 2398336, {512},   net:get(7).bias) 
    ParamBank:read( 2398848, {512,512,3,3}, net:get(9).weight) 
    ParamBank:read( 4758144, {512},   net:get(9).bias) 
    ParamBank:read( 4758656, {1024,512,3,3}, net:get(11).weight) 
    ParamBank:read( 9477248, {1024},   net:get(11).bias) 
    ParamBank:read( 9478272, {1024,1024,3,3}, net:get(13).weight) 
    ParamBank:read(18915456, {1024},   net:get(13).bias) 
    ParamBank:read(18916480, {4096,1024,5,5}, net:get(16).weight) 
    ParamBank:read(123774080, {4096},   net:get(16).bias) 
    ParamBank:read(123778176, {4096,4096,1,1}, net:get(18).weight) 
    ParamBank:read(140555392, {4096},   net:get(18).bias) 
    ParamBank:read(140559488, {1000,4096,1,1}, net:get(20).weight) 
    ParamBank:read(144655488, {1000},   net:get(20).bias) 

    ParamBank:close() 

    -- load and preprocess image 
    print('==> prepare an input image') 
    local img = image.load(opt.img):mul(255) 

    -- use image larger than the eye size in spatial mode 
    if not opt.spatial then 
    local dim = (opt.network == 'small') and 231 or 221 
    local img_scale = image.scale(img, '^'..dim) 
    local h = math.ceil((img_scale:size(2) - dim)/2) 
    local w = math.ceil((img_scale:size(3) - dim)/2) 
    img = image.crop(img_scale, w, h, w + dim, h + dim):floor() 
    end 

    -- memcpy from system RAM to GPU RAM if cuda enabled 
    if opt.backend == 'cunn' or opt.backend == 'cudnn' then 
    net:cuda() 
    img = img:cuda() 
    end 

    -- save bare network (before its buffer filled with temp results) 
    print('==> save model to:', opt.save) 
    torch.save(opt.save, net) 

    -- feedforward network 
    print('==> feed the input image') 
    timer = torch.Timer() 
    img:add(-118.380948):div(61.896913) 
    local out = net:forward(img) 

    -- find output class name in non-spatial mode 
    local results = {} 
    local topN = 10 
    local probs, idxs = torch.topk(out, topN, 1, true) 

    for i=1,topN do 
    print(label[idxs[i]], probs[i]) 
    local r = {} 
    r.label = label[idxs[i]] 
    r.prob = probs[i] 
    results[i] = r 
    end 

    return results 
end 

function errorHandler(err) 
    return tostring(err) 
end 

local success, result = xpcall(classifyImage, errorHandler) 


context.template = { 
    type = "mustache", 
    name = "app/templates/layout", 

    partials = { 
    content = "app/templates/classify", 
    } 
} 


context.output = { 
    success = success, 
    result = result, 
    request = context.input 
} 

context.response.status = 200 

感謝您的幫助!

更新1

新增print(net)之前和之後local net而且之後我打電話net:add。每次在local net初始化之前,它顯示的值爲nil。正如預期的那樣,在初始化net之後,它顯示了一個火炬對象作爲值。看樣子:add調用裏面的東西被創造的錯誤,所以我加了聲明我classifyImage功能後立即以下幾點:

print(tostring(torch)) 
print(tostring(nn)) 
print(tostring(net)) 

添加這些新的打印報表後,我得到的一號請求以下

nil 
nil 
nil 

,然後在第二個請求:

table: 0x41448a08 
table: 0x413bdb10 
nil 

和位於3要求:

table: 0x41448a08 
table: 0x413bdb10 
nil 

那些看起來像指向內存中的對象的指針,所以在這裏假設Torch正在創建它自己的全局對象是安全的嗎?

+0

嘗試在調用之前和之後放置'print(net)'。 – hjpotter92

+0

很快完成並在問題中添加詳細信息。本質上,在我在第一/第二次調用中刪除「本地網絡」之前,我成功地獲得了'nil'。初始化'net'後,我也得到一個新的對象。只有當我調用add時,它纔會失敗。你認爲這與'torch'或'nn'本身有關? – crockpotveggies

+0

@ hjpotter92增加了一些更多的信息,看起來像'torch'本身正在創建內存中的干擾代碼的全局對象? – crockpotveggies

回答

0

當需要torch及其模塊時,它最終創建一個自身的全局實例,該實例在整個過程的整個過程中保留在內存中。爲我工作的修復是引用火炬在主app.lua文件中精力充沛並粘貼以下頂部:

require 'torch' 
require 'nn' 

image = require 'image' 
ParamBank = require 'ParamBank' 
label  = require 'classifier_label' 
torch.setdefaulttensortype('torch.FloatTensor') 
torch.setnumthreads(4) 

SpatialConvolution = nn.SpatialConvolutionMM 
SpatialMaxPooling = nn.SpatialMaxPooling 
ReLU = nn.ReLU 
SpatialSoftMax = nn.SpatialSoftMax 

的變量範圍爲classifyImage,現在它的每個請求成功。這是一個骯髒的問題,但由於Torch正在維護它自己的全局對象,所以我無法看到它的解決方法。

相關問題