def prepBenchm():
cb.clearMemory(m)
for frame in frameset[:-1]:
m(
torch.autograd.Variable(frame,
volatile=True,
requires_grad=False))
if cuda:
torch.cuda.synchronize()
def inferFrameset(m, frameset, cuda=True, preprocessor=None, postproc=None):
if preprocessor is not None:
frameset = list(map(preprocessor, frameset))
if cuda:
frameset = [frm.cuda() for frm in frameset]
cb.clearMemory(m)
for frame in frameset:
y = m(
torch.autograd.Variable(frame, volatile=True, requires_grad=False))
if postproc is not None:
y = postproc(y)
return y
def getModels(experimentIdx):
experimentIdx = 11
modelBaseline = op.PoseModel.fromFile(T=2).eval()
if experimentIdx <= 8:
modelTest = torch.load('models/model3.net')
elif experimentIdx == 9:
modelTest = torch.load('models/model009.net')
elif experimentIdx == 10:
modelTest = torch.load('models/model010.net'
) # experiment 10 -- trained for recursive
elif experimentIdx == 11:
modelTest = torch.load(
'models/model011c.net'
) # recursive AND with optimized threshold selection
# a: straight-forward, b: ???, c: no pre-init of thresholds for whole block
else:
assert (False)
pycbinfer.clearMemory(modelTest)
return modelTest, modelBaseline
def inferFramesetPowerMeasurement(m,
frameset,
cuda=True,
numFrames=0,
preprocessor=None):
if preprocessor is not None:
frameset = list(map(preprocessor, frameset))
if cuda:
frameset = [frm.cuda() for frm in frameset]
#create a longer sequence by going back-and-forth on the frames we have
if numFrames > 0:
frameset = frameset + frameset[-2:0:-1]
frameset = math.ceil(numFrames / len(frameset)) * frameset
frameset = frameset[:numFrames]
frame = frameset[0]
cb.clearMemory(m)
m(torch.autograd.Variable(frame, volatile=True, requires_grad=False))
if cuda:
torch.cuda.synchronize()
pl = tx2power.PowerLogger(
interval=1.0, #interval=0.05,
nodes=tx2power.getNodesByName(nameList=[
'board/main',
'module/main',
# 'module/cpu','module/gpu','module/ddr'
]))
pl.start()
for fid, frame in enumerate(frameset[1:]):
m(torch.autograd.Variable(frame, volatile=True, requires_grad=False))
# torch.cuda.synchronize()
# pl.recordEvent('completed frame %d' % (fid,))
torch.cuda.synchronize()
pl.stop()
return pl
for m in cbconvModules:
m.feedbackLoop = False
#apply threshold factor
cbconvThresholds = list(map(lambda m: m.threshold, cbconvModules))
for th, m in zip(cbconvThresholds, cbconvModules):
m.threshold = thFactor * th
#%% load data
import videoSequenceReader as vsr # select data loader and thus dataset
frameset, target = vsr.getDataFrames(seqName=seqName, numFrames=numFrames)
#apply preprocessing
frameset = list(map(poseDetEvaluator.preprocessor, frameset))
#%% trace 1 & 2: accuracy / loss & no. operations
cb.clearMemory(modelTest)
for m in cbconvModules:
m.gatherComputationStats = True
lossTrace, opsTrace, outpVarTrace = [], [], []
for t, frm in enumerate(frameset):
outpRef = poseDetEvaluator.modelApply(frm, modelBaseline)
outpAct = poseDetEvaluator.modelApply(frm, modelTest)
loss = poseDetEvaluator.evaluator(
[outpAct], [outpRef],
method='maxAbsDiff') # non_MSE metric is being used (!!)
# loss = poseDetEvaluator.evaluator([outpAct], [outpRef], method='mse')
lossTrace.append(loss)
outpVarTrace.append(outpRef.var())
numOps = reduce(
lambda u, v: u + v,
else:
poseModel = op.PoseModel.fromFile(T=2)
# poseModel.timed = True # enable priting timing results
# finegrained = True
if useCBinfer:
poseModel.model0 = cb.convert(poseModel.model0)
poseModel.model1_1 = cb.convert(poseModel.model1_1)
poseModel.model1_2 = cb.convert(poseModel.model1_2)
poseModel.model2_1 = cb.convert(poseModel.model2_1)
poseModel.model2_2 = cb.convert(poseModel.model2_2)
poseModel.timed = measureTiming
if gpu:
poseModel.cuda()
else:
poseModel.cpu()
cb.clearMemory(poseModel)
poseDet = op.PoseDetector(poseModel)
#poseModel.model0[0].finegrained = True
#poseModel.model0[0].threshold *= 0.1
#visualize first change map: plt.imshow(poseModel.model0[0].changeMap.cpu().float().numpy())
# print run time: poseModel.timed = True
frames, _ = vsr.getDataFrames(seqName=seqName, numFrames=numFrame)
if gpu:
torch.cuda.synchronize()
##ANALYSIS 1: visualize several changeMaps
#changeMapsVis = [str(v) for v in [0,2,12,25]]
#for cmi in changeMapsVis: