def validate(val_loader, model, criterion, adaptation):
# switch to evaluate mode
run_time = time.time()
matrix = ConfusionMatrix(args['label_nums'])
loss = 0
for i, (images, labels) in enumerate(val_loader):
labels = labels.cuda(async=True)
target_var = torch.autograd.Variable(labels, volatile=True)
model.test(adaptation, images)
output = model.output
loss += criterion(output, target_var)/args['batch_size']
matrix = update_confusion_matrix(matrix, output.data, labels)
loss /= (i+1)
run_time = time.time() - run_time
logger.info('=================================================')
logger.info('val:'
'loss: {0:.4f}\t'
'accuracy: {1:.4f}\t'
'fg_accuracy: {2:.4f}\t'
'avg_precision: {3:.4f}\t'
'avg_recall: {4:.4f}\t'
'avg_f1score: {5:.4f}\t'
'run_time:{run_time:.2f}\t'
.format(loss.data[0], matrix.accuracy(),
matrix.fg_accuracy(), matrix.avg_precision(), matrix.avg_recall(), matrix.avg_f1score(),run_time=run_time))
logger.info('=================================================')
return matrix.all_acc()
def main():
if len(args['device_ids']) > 0:
torch.cuda.set_device(args['device_ids'][0])
test_loader = data.DataLoader(imageLabelLoader(args['data_path'],
dataName=args['domainB'],
phase='val'),
batch_size=args['batch_size'],
num_workers=args['num_workers'],
shuffle=False)
gym = deeplabG1G2()
gym.initialize(args)
gym.load(
'/home/ben/mathfinder/PROJECT/AAAI2017/our_Method/v3/deeplab_feature_adaptation/checkpoints/Lip_to_July_lr_g1=0.00001_lr_g2=0.00000002_interval_g1=5_interval_d1=5_net_D=lsganMultOutput_D_if_adaptive=True_resume_decay=g2/best_Ori_on_B_model.pth'
)
gym.eval()
matrix = ConfusionMatrix(args['label_nums'])
for i, (image, label) in enumerate(test_loader):
label = label.cuda(async=True)
target_var = torch.autograd.Variable(label, volatile=True)
gym.test(image)
output = gym.output
matrix = update_confusion_matrix(matrix, output.data, label)
print(matrix.all_acc())
print(matrix.f1score())
