arg.save_dir = "%s/outs/%s"%(os.getcwd(), arg.save_dir)
if os.path.exists(arg.save_dir) is False:
os.mkdir(arg.save_dir)
logger = Logger(arg.save_dir)
copyreg.pickle(torch.dtype, pickle_torch_dtype)
os.environ["CUDA_VISIBLE_DEVICES"] = arg.gpus
torch_device = torch.device("cuda")
preprocess = preprocess.get_preprocess(arg.augment)
train_loader = nucleusloader(f_path_train, arg.batch_size, transform=preprocess,
cpus=arg.cpus,
shuffle=True, drop_last=True)
valid_loader = nucleusloader3(f_path_valid, batch_size=1, transform=None,
cpus=arg.cpus, shuffle=False,
drop_last=True)
if arg.model == "fusion":
net = Fusionnet(arg.in_channel, arg.out_channel, arg.ngf, arg.clamp)
elif arg.model == "unet":
net = Unet3D(feature_scale=arg.feature_scale)
elif arg.model == "unet_gh":
## "nets_1004_unet_glob_absloss_FRE_pw10_erode2_feat1_trans30"
#net = Unet3D_glob2(feature_scale=arg.feature_scale, trans_feature=64)
#net = Unet3D_glob(feature_scale=arg.feature_scale, trans_feature=64)
erode=3,
backzero=backzero)
model = CNNTrainer(arg,
net,
torch_device,
recon_loss=recon_loss,
val_loss=val_loss,
logger=logger)
#model.load(filename="epoch[0402]_losssum[0.016887].pth.tar")
model.load(filename="epoch[0493]_losssum[0.015393].pth.tar")
######phase 1######
test_loader = nucleusloader(f_path_test + '/dataset1/exp0_fullsequence',
batch_size=1,
transform=None,
cpus=arg.cpus,
shuffle=False,
drop_last=True)
model.test(test_loader, savedir='dataset1')
######phase 2######
#listdir=os.listdir(f_path_test+'/dataset2')
#for ld in listdir:
# if ld.find('2018')!=0:
# test_loader = nucleusloader(f_path_test+'/dataset2/'+ld, batch_size=1, transform=None,
# cpus=arg.cpus, shuffle=False,
# drop_last=True)
# model.test(test_loader,savedir='dataset2_'+ld)
# for ld in listdir: