I have a Lusty (framework for OpenResty) API that wraps a Torch classifier. So far, I've been able to get a single request to work, however each subsequent request to the API triggers the following error with no detailed stack trace:
attempt to index a nil value
The error appears to be thrown when I call:
net:add(SpatialConvolution(3, 96, 7, 7, 2, 2))
The behavior of successfully completing the 1st request while failing with each additional request is a clue to the problem.
I've pasted the full code below for app/requests/classify.lua. This appears to be some sort of variable caching/initialization issue, though my limited knowledge of Lua isn't helping me debug the problem. I've tried doing multiple things, including changing my imports to localized variables like local torch = require('torch') and also moving those imports to inside the classifyImage() function.
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
Appreciate your help!
Update 1
Added print( net ) before and after local net and also after I call net:add. Each time before local net is initialized, it shows the value as nil. As expected, after initializing net it shows a torch object as the value. It appears something inside the :add call is creating the error, so I added the following immediately after declaring my classifyImage function:
print(tostring(torch))
print(tostring(nn))
print(tostring(net))
After adding those new print statements, I get the following on the 1st request:
nil
nil
nil
And then on the 2nd request:
table: 0x41448a08
table: 0x413bdb10
nil
And on the 3rd request:
table: 0x41448a08
table: 0x413bdb10
nil
Those look like pointers to an object in memory, so is it safe to assume here that Torch is creating its own global object?
print(net)before and after the calls. – hjpotter92local netin both the 1st/2nd calls I successfully getnil. After initializingnetI also get a new object. It's only when I calladddoes it fail. You think it's something related totorchornnitself? – crockpotveggiestorchitself is creating global objects in memory that are interfering with the code? – crockpotveggies