def load_net():
encoder_param = load_lua(
'../../models_anti_multi_level_pyramid_stage_decoder_in/vgg_normalised_conv5_1.t7'
)
net_e = encoder(encoder_param)
net_d0 = decoder0()
net_d0.load_state_dict(
torch.load(
'./trained_models_anti_multi_level/decoder_epoch_5.pth.tar'))
net_d1 = decoder1()
net_d1.load_state_dict(
torch.load(
'./trained_models_anti_multi_level/decoder_epoch_5.pth.tar'))
net_d2 = decoder2()
net_d2.load_state_dict(
torch.load(
'./trained_models_anti_multi_level/decoder_epoch_5.pth.tar'))
net_d3 = decoder3()
net_d3.load_state_dict(
torch.load(
'./trained_models_anti_multi_level/decoder_epoch_5.pth.tar'))
net_d4 = decoder4()
net_d4.load_state_dict(
torch.load(
'./trained_models_anti_multi_level/decoder_epoch_5.pth.tar'))
net_d5 = decoder5()
net_d5.load_state_dict(
torch.load(
'./trained_models_anti_multi_level/decoder_epoch_5.pth.tar'))
return net_e, net_d0, net_d1, net_d2, net_d3, net_d4, net_d5
def load_net():
encoder_param = load_lua('/mnt/home/xiaoxiang/haozhe/style_nas_2/models/models_photorealistic_nas/vgg_normalised_conv5_1.t7')
net_e = encoder(encoder_param)
net_d0 = decoder0()
net_d0.load_state_dict(torch.load(os.path.join(abs_dir, 'trained_models_nas/decoder_epoch_2.pth.tar')))
net_d1 = decoder1()
net_d1.load_state_dict(torch.load(os.path.join(abs_dir, 'trained_models_nas/decoder_epoch_2.pth.tar')))
net_d2 = decoder2()
net_d2.load_state_dict(torch.load(os.path.join(abs_dir, 'trained_models_nas/decoder_epoch_2.pth.tar')))
net_d3 = decoder3()
net_d3.load_state_dict(torch.load(os.path.join(abs_dir, 'trained_models_nas/decoder_epoch_2.pth.tar')))
net_d4 = decoder4()
net_d4.load_state_dict(torch.load(os.path.join(abs_dir, 'trained_models_nas/decoder_epoch_2.pth.tar')))
net_d5 = decoder5()
net_d5.load_state_dict(torch.load(os.path.join(abs_dir, 'trained_models_nas/decoder_epoch_2.pth.tar')))
return net_e, net_d0, net_d1, net_d2, net_d3, net_d4, net_d5
def load_net():
encoder_param = load_lua(
'/home/zouyj/projects/style_transfer/stylenas/models_photorealistic_nas/vgg_normalised_conv5_1.t7'
)
net_e = encoder(encoder_param)
net_d0 = decoder0()
net_d0.load_state_dict(
torch.load(
os.path.join(abs_dir,
'trained_models_aaai/decoder_epoch_2.pth.tar')))
net_d1 = decoder1()
net_d1.load_state_dict(
torch.load(
os.path.join(abs_dir,
'trained_models_aaai/decoder_epoch_2.pth.tar')))
net_d2 = decoder2()
net_d2.load_state_dict(
torch.load(
os.path.join(abs_dir,
'trained_models_aaai/decoder_epoch_2.pth.tar')))
net_d3 = decoder3()
net_d3.load_state_dict(
torch.load(
os.path.join(abs_dir,
'trained_models_aaai/decoder_epoch_2.pth.tar')))
net_d4 = decoder4()
net_d4.load_state_dict(
torch.load(
os.path.join(abs_dir,
'trained_models_aaai/decoder_epoch_2.pth.tar')))
net_d5 = decoder5()
net_d5.load_state_dict(
torch.load(
os.path.join(abs_dir,
'trained_models_aaai/decoder_epoch_2.pth.tar')))
return net_e, net_d0, net_d1, net_d2, net_d3, net_d4, net_d5