2020-1-capstone-design2 / 2016104167

Go to a project
Toggle navigation Toggle navigation pinning
조현아
a5ce1660 1 parent c4e3768c

resolved classify acc err

Inline Side-by-side
Showing 3 changed files with 102 additions and 49 deletions
......@@ -5,19 +5,19 @@ from pprint import pprint
import torch
import torch.nn as nn
from torch.utils.tensorboard import SummaryWriter
import torchvision.transforms as transforms
#from torch.utils.tensorboard import SummaryWriter
from utils import *
# command
# python eval.py --model_path='logs/April_16_00:26:10__resnet50__None/'
def eval(model_path, num_data):
def eval(model_path):
print('\n[+] Parse arguments')
kwargs_path = os.path.join(model_path, 'kwargs.json')
kwargs = json.loads(open(kwargs_path).read())
args, kwargs = parse_args(kwargs)
args.batch_size = num_data
pprint(args)
device = torch.device('cuda' if args.use_cuda else 'cpu')
......@@ -35,23 +35,25 @@ def eval(model_path, num_data):
model.load_state_dict(torch.load(weight_path))
print('\n[+] Load dataset')
test_dataset = get_dataset(args, 'test')
transform = transforms.Compose([
transforms.Resize([240, 240]),
transforms.ToTensor()
])
test_dataset = get_dataset(args, transform, 'test')
test_loader = iter(get_dataloader(args, test_dataset)) ###
print('\n[+] Start testing')
writer = SummaryWriter(log_dir=model_path)
_test_res = validate(args, model, criterion, test_loader, step=0, writer=writer)
# print('\n[+] Start testing')
# writer = SummaryWriter(log_dir=model_path)
_test_res = validate(args, model, criterion, test_loader, step=0)
print('\n[+] Valid results')
print(' Acc@1 : {:.3f}%'.format(_test_res[0].data.cpu().numpy()[0]*100))
print(' Acc@5 : {:.3f}%'.format(_test_res[1].data.cpu().numpy()[0]*100))
print(' Acc_all : {:.3f}%'.format(_test_res[2].data.cpu().numpy()[0]*100))
print(' Loss : {:.3f}'.format(_test_res[3].data))
print(' Infer Time(per image) : {:.3f}ms'.format(_test_res[4]*1000 / len(test_dataset)))
print(' Loss : {:.3f}'.format(_test_res[1].data))
print(' Infer Time(per image) : {:.3f}ms'.format(_test_res[2]*1000 / len(test_dataset)))
writer.close()
#writer.close()
if __name__ == '__main__':
fire.Fire(eval)
......
......@@ -7,7 +7,7 @@ from pprint import pprint
import torch.nn as nn
import torch.backends.cudnn as cudnn
from torch.utils.tensorboard import SummaryWriter
#from torch.utils.tensorboard import SummaryWriter
from networks import *
from utils import *
......@@ -27,7 +27,7 @@ def train(**kwargs):
log_dir = os.path.join('/content/drive/My Drive/CD2 Project/runs/classify/', model_name)
os.makedirs(os.path.join(log_dir, 'model'))
json.dump(kwargs, open(os.path.join(log_dir, 'kwargs.json'), 'w'))
writer = SummaryWriter(log_dir=log_dir)
#writer = SummaryWriter(log_dir=log_dir)
if args.seed is not None:
random.seed(args.seed)
......@@ -45,8 +45,10 @@ def train(**kwargs):
#writer.add_graph(model)
print('\n[+] Load dataset')
train_dataset = get_dataset(args, 'train')
valid_dataset = get_dataset(args, 'val')
transform = get_train_transform(args, model, log_dir)
val_transform = get_valid_transform(args, model)
train_dataset = get_dataset(args, transform, 'train')
valid_dataset = get_dataset(args, val_transform, 'val')
train_loader = iter(get_inf_dataloader(args, train_dataset))
max_epoch = len(train_dataset) // args.batch_size
best_acc = -1
......@@ -62,16 +64,16 @@ def train(**kwargs):
start_t = time.time()
for step in range(args.start_step, args.max_step):
batch = next(train_loader)
_train_res = train_step(args, model, optimizer, scheduler, criterion, batch, step, writer)
_train_res = train_step(args, model, optimizer, scheduler, criterion, batch, step)
if step % args.print_step == 0:
print('\n[+] Training step: {}/{}\tTraining epoch: {}/{}\tElapsed time: {:.2f}min\tLearning rate: {}'.format(
step, args.max_step, current_epoch, max_epoch, (time.time()-start_t)/60, optimizer.param_groups[0]['lr']))
writer.add_scalar('train/learning_rate', optimizer.param_groups[0]['lr'], global_step=step)
writer.add_scalar('train/acc1', _train_res[0], global_step=step)
writer.add_scalar('train/loss', _train_res[1], global_step=step)
writer.add_scalar('train/forward_time', _train_res[2], global_step=step)
writer.add_scalar('train/backward_time', _train_res[3], global_step=step)
# writer.add_scalar('train/learning_rate', optimizer.param_groups[0]['lr'], global_step=step)
# writer.add_scalar('train/acc1', _train_res[0], global_step=step)
# writer.add_scalar('train/loss', _train_res[1], global_step=step)
# writer.add_scalar('train/forward_time', _train_res[2], global_step=step)
# writer.add_scalar('train/backward_time', _train_res[3], global_step=step)
print(' Acc@1 : {:.3f}%'.format(_train_res[0].data.cpu().numpy()[0]*100))
print(' Loss : {}'.format(_train_res[1].data))
print(' FW Time : {:.3f}ms'.format(_train_res[2]*1000))
......@@ -80,10 +82,10 @@ def train(**kwargs):
if step % args.val_step == args.val_step-1:
# print("\nstep, args.val_step: ", step, args.val_step)
valid_loader = iter(get_dataloader(args, valid_dataset))
_valid_res = validate(args, model, criterion, valid_loader, step, writer)
print('\n[+] Valid results')
writer.add_scalar('valid/acc1', _valid_res[0], global_step=step)
writer.add_scalar('valid/loss', _valid_res[1], global_step=step)
_valid_res = validate(args, model, criterion, valid_loader, step)
print('\n[+] (Valid results) Valid step: {}/{}'.format(step, args.max_step))
# writer.add_scalar('valid/acc1', _valid_res[0], global_step=step)
# writer.add_scalar('valid/loss', _valid_res[1], global_step=step)
print(' Acc@1 : {:.3f}%'.format(_valid_res[0].data.cpu().numpy()[0]*100))
print(' Loss : {}'.format(_valid_res[1].data))
......@@ -92,7 +94,7 @@ def train(**kwargs):
torch.save(model.state_dict(), os.path.join(log_dir, "model","model.pt"))
print('\n[+] Model saved')
writer.close()
# writer.close()
if __name__ == '__main__':
......
......@@ -23,6 +23,7 @@ from sklearn.model_selection import KFold
from networks import basenet, grayResNet2
DATASET_PATH = '/content/drive/My Drive/CD2 Project/'
TRAIN_DATASET_PATH = '/content/drive/My Drive/CD2 Project/data/nonaug+Normal_train/'
TRAIN_TARGET_PATH = '/content/drive/My Drive/CD2 Project/data/train_nonaug_classify_target.csv'
......@@ -131,17 +132,17 @@ def parse_args(kwargs):
kwargs['dataset'] = kwargs['dataset'] if 'dataset' in kwargs else 'BraTS'
kwargs['network'] = kwargs['network'] if 'network' in kwargs else 'resnet50'
kwargs['optimizer'] = kwargs['optimizer'] if 'optimizer' in kwargs else 'adam'
kwargs['learning_rate'] = kwargs['learning_rate'] if 'learning_rate' in kwargs else 0.001
kwargs['learning_rate'] = kwargs['learning_rate'] if 'learning_rate' in kwargs else 0.01
kwargs['seed'] = kwargs['seed'] if 'seed' in kwargs else None
kwargs['use_cuda'] = kwargs['use_cuda'] if 'use_cuda' in kwargs else True
kwargs['use_cuda'] = kwargs['use_cuda'] and torch.cuda.is_available()
kwargs['num_workers'] = kwargs['num_workers'] if 'num_workers' in kwargs else 4
kwargs['print_step'] = kwargs['print_step'] if 'print_step' in kwargs else 100
kwargs['val_step'] = kwargs['val_step'] if 'val_step' in kwargs else 100
kwargs['print_step'] = kwargs['print_step'] if 'print_step' in kwargs else 50
kwargs['val_step'] = kwargs['val_step'] if 'val_step' in kwargs else 50
kwargs['scheduler'] = kwargs['scheduler'] if 'scheduler' in kwargs else 'exp'
kwargs['batch_size'] = kwargs['batch_size'] if 'batch_size' in kwargs else 32
kwargs['batch_size'] = kwargs['batch_size'] if 'batch_size' in kwargs else 16
kwargs['start_step'] = kwargs['start_step'] if 'start_step' in kwargs else 0
kwargs['max_step'] = kwargs['max_step'] if 'max_step' in kwargs else 2500
kwargs['max_step'] = kwargs['max_step'] if 'max_step' in kwargs else 500
kwargs['augment_path'] = kwargs['augment_path'] if 'augment_path' in kwargs else None
# to named tuple
......@@ -155,11 +156,10 @@ def select_model(args):
'resnet50':grayResNet2.resnet50(), 'resnet101':grayResNet2.resnet101(), 'resnet152':grayResNet2.resnet152()}
if args.network in resnet_dict:
backbone = resnet_dict[args.network]
model = basenet.BaseNet(backbone, args)
else:
Net = getattr(importlib.import_module('networks.{}'.format(args.network)), 'Net')
model = Net(args)
model = resnet_dict[args.network]
# else: # 3 channels
# backbone = models.__dict__[args.network]()
# model = basenet.BaseNet(backbone, args)
#print(model) # print model architecture
return model
......@@ -187,16 +187,44 @@ def select_scheduler(args, optimizer):
else:
raise Exception('Unknown Scheduler')
def get_train_transform(args, model, transform, log_dir=None):
if args.dataset == 'cifar10':
transform = transforms.Compose([
transforms.Pad(4),
transforms.RandomCrop(32),
transforms.RandomHorizontalFlip(),
transforms.ToTensor()
])
else:
transform = transforms.Compose([
transforms.Resize([240, 240]),
transforms.ToTensor()
])
return transform
def get_valid_transform(args, model):
if args.dataset == 'cifar10':
val_transform = transforms.Compose([
transforms.Resize(32),
transforms.ToTensor()
])
else:
val_transform = transforms.Compose([
transforms.Resize([240, 240]),
transforms.ToTensor()
])
return val_transform
class CustomDataset(Dataset):
def __init__(self, data_path, csv_path):
def __init__(self, data_path, csv_path, transform):
self.path = data_path
self.imgs = natsorted(os.listdir(data_path))
self.len = len(self.imgs)
self.transform = transforms.Compose([
transforms.Resize([240, 240]),
transforms.ToTensor()
])
self.transform = transform
df = pd.read_csv(csv_path)
targets_list = []
......@@ -215,6 +243,7 @@ class CustomDataset(Dataset):
targets = self.targets[idx]
image = Image.open(img_loc)
image = self.transform(image)
#print("\n idx, img, targets: ", idx, img_loc, targets)
return image, targets
......@@ -222,12 +251,32 @@ class CustomDataset(Dataset):
def get_dataset(args, transform, split='train'):
assert split in ['train', 'val', 'test']
if args.dataset == 'cifar10':
train = split in ['train', 'val', 'trainval']
dataset = torchvision.datasets.CIFAR10(DATASET_PATH,
train=train,
transform=transform,
download=True)
if split in ['train', 'val']:
split_path = os.path.join(DATASET_PATH,
'cifar-10-batches-py', 'train_val_index.cp')
if not os.path.exists(split_path):
[train_index], [val_index] = split_dataset(args, dataset, k=1)
split_index = {'train':train_index, 'val':val_index}
cp.dump(split_index, open(split_path, 'wb'))
split_index = cp.load(open(split_path, 'rb'))
dataset = Subset(dataset, split_index[split])
else:
if split in ['train']:
dataset = CustomDataset(TRAIN_DATASET_PATH, TRAIN_TARGET_PATH)
dataset = CustomDataset(TRAIN_DATASET_PATH, TRAIN_TARGET_PATH, transform)
elif split in ['val']:
dataset = CustomDataset(VAL_DATASET_PATH, VAL_TARGET_PATH)
dataset = CustomDataset(VAL_DATASET_PATH, VAL_TARGET_PATH, transform)
else : # test
dataset = CustomDataset(TEST_DATASET_PATH, TEST_TARGET_PATH)
dataset = CustomDataset(TEST_DATASET_PATH, TEST_TARGET_PATH, transform)
return dataset
......@@ -261,7 +310,7 @@ def get_inf_dataloader(args, dataset):
def train_step(args, model, optimizer, scheduler, criterion, batch, step, writer, device=None):
def train_step(args, model, optimizer, scheduler, criterion, batch, step, device=None):
model.train()
images, target = batch
......@@ -275,7 +324,7 @@ def train_step(args, model, optimizer, scheduler, criterion, batch, step, writer
# compute output
start_t = time.time()
output, first = model(images)
output= model(images)
forward_t = time.time() - start_t
loss = criterion(output, target)
......@@ -323,7 +372,7 @@ def accuracy(output, target, topk=(1,)):
res.append(correct_k)
return res
def validate(args, model, criterion, valid_loader, step, writer, device=None):
def validate(args, model, criterion, valid_loader, step, device=None):
# switch to evaluate mode
model.eval()
......@@ -344,7 +393,7 @@ def validate(args, model, criterion, valid_loader, step, writer, device=None):
target = target.cuda(non_blocking=True)
# compute output
output, first = model(images)
output = model(images)
loss = criterion(output, target)
infer_t += time.time() - start_t
......