param.requires_grad = False
for param in albedoDecoders[n].parameters():
param.requires_grad = False
for param in normalDecoders[n].parameters():
param.requires_grad = False
for param in roughDecoders[n].parameters():
param.requires_grad = False
for param in depthDecoders[n].parameters():
param.requires_grad = False
if opt.isLight or (opt.level == 2 and n == 0):
# Light network
lightEncoders.append(
models.encoderLight(cascadeLevel=n, SGNum=opt.SGNum).eval())
axisDecoders.append(
models.decoderLight(mode=0, SGNum=opt.SGNum).eval())
lambDecoders.append(
models.decoderLight(mode=1, SGNum=opt.SGNum).eval())
weightDecoders.append(
models.decoderLight(mode=2, SGNum=opt.SGNum).eval())
lightEncoders[n].load_state_dict(
torch.load('{0}/lightEncoder{1}_{2}.pth'.format(
experimentsLight[n], n, nepochsLight[n] - 1)).state_dict())
axisDecoders[n].load_state_dict(
torch.load('{0}/axisDecoder{1}_{2}.pth'.format(
experimentsLight[n], n, nepochsLight[n] - 1)).state_dict())
lambDecoders[n].load_state_dict(
torch.load('{0}/lambDecoder{1}_{2}.pth'.format(
experimentsLight[n], n, nepochsLight[n] - 1)).state_dict())
weightDecoders[n].load_state_dict(
# Initial Network
encoder = models.encoder0(cascadeLevel = 0 )
albedoDecoder = models.decoder0(mode=0 )
normalDecoder = models.decoder0(mode=1 )
roughDecoder = models.decoder0(mode=2 )
depthDecoder = models.decoder0(mode=4 )
encoder1 = models.encoder0(cascadeLevel = 1 )
albedoDecoder1 = models.decoder0(mode=0 )
normalDecoder1 = models.decoder0(mode=1 )
roughDecoder1 = models.decoder0(mode=2 )
depthDecoder1 = models.decoder0(mode=4 )
lightEncoder = models.encoderLight(cascadeLevel = 0, SGNum = opt.SGNum )
axisDecoder = models.decoderLight(mode=0, SGNum = opt.SGNum )
lambDecoder = models.decoderLight(mode = 1, SGNum = opt.SGNum )
weightDecoder = models.decoderLight(mode = 2, SGNum = opt.SGNum )
renderLayer = models.renderingLayer(isCuda = opt.cuda,
imWidth=opt.envCol, imHeight=opt.envRow,
envWidth = opt.envWidth, envHeight = opt.envHeight)
output2env = models.output2env(isCuda = opt.cuda,
envWidth = opt.envWidth, envHeight = opt.envHeight, SGNum = opt.SGNum )
####################################################################
#########################################
encoder.load_state_dict(
torch.load('{0}/encoder{1}_{2}.pth'.format(opt.experimentBRDF0, 0,