def main():
parser = argparse.ArgumentParser()
parser.add_argument('--batch_size', type=int, default=32)
parser.add_argument('--epochs', type=int, default=50)
parser.add_argument('--num_classes', type=int, default=130)
parser.add_argument('--lr', type=float, default=2e-3)
parser.add_argument('--weight_decay', type=float, default=1e-5)
parser.add_argument('--resume', type=bool, default=False)
parser.add_argument('--eval', type=bool, default=False)
parser.add_argument('--dataroot', type=str, default='/content/drive/MyDrive/dogflg/data2/')
parser.add_argument('--model_path', type=str, default='./best_model.bin')
parser.add_argument('--sampleratio', type=float, default=0.8)
args = parser.parse_args()
transform_train = transform.Compose([
transform.Resize((256, 256)),
transform.CenterCrop(224),
transform.RandomHorizontalFlip(),
transform.ToTensor(),
transform.ImageNormalize(0.485, 0.229),
# transform.ImageNormalize(0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
])
root_dir = args.dataroot
train_loader = TsinghuaDog(root_dir, batch_size=args.batch_size, train=True, part='train', shuffle=True, transform=transform_train, sample_rate=args.sampleratio)
transform_test = transform.Compose([
transform.Resize((256, 256)),
transform.CenterCrop(224),
transform.ToTensor(),
transform.ImageNormalize(0.485, 0.229),
# transform.ImageNormalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
])
val_loader = TsinghuaDog(root_dir, batch_size=args.batch_size, train=False, part='val', shuffle=False, transform=transform_test, sample_rate=args.sampleratio)
epochs = args.epochs
model = Net(num_classes=args.num_classes)
lr = args.lr
weight_decay = args.weight_decay
optimizer = SGD(model.parameters(), lr=lr, momentum=0.99)
if args.resume:
model.load(args.model_path)
print('model loaded', args.model_path)
#random save for test
#model.save(args.model_path)
if args.eval:
evaluate(model, val_loader, save_path=args.model_path)
return
for epoch in range(epochs):
train(model, train_loader, optimizer, epoch)
evaluate(model, val_loader, epoch, save_path=args.model_path)
def test_crop(self):
height = random.randint(10, 32) * 2
width = random.randint(10, 32) * 2
oheight = random.randint(5, (height - 2) / 2) * 2
owidth = random.randint(5, (width - 2) / 2) * 2
img = np.ones([height, width, 3])
oh1 = (height - oheight) // 2
ow1 = (width - owidth) // 2
# imgnarrow = img[oh1:oh1 + oheight, ow1:ow1 + owidth, :]
# imgnarrow.fill(0)
img[oh1:oh1 + oheight, ow1:ow1 + owidth, :] = 0
# img = jt.array(img)
result = transform.Compose([
transform.ToPILImage(),
transform.CenterCrop((oheight, owidth)),
transform.ToTensor(),
])(img)
self.assertEqual(
result.sum(), 0,
f"height: {height} width: {width} oheight: {oheight} owdith: {owidth}"
)
oheight += 1
owidth += 1
result = transform.Compose([
transform.ToPILImage(),
transform.CenterCrop((oheight, owidth)),
transform.ToTensor(),
])(img)
sum1 = result.sum()
# TODO: not pass
# self.assertGreater(sum1, 1,
# f"height: {height} width: {width} oheight: {oheight} owdith: {owidth}")
oheight += 1
owidth += 1
result = transform.Compose([
transform.ToPILImage(),
transform.CenterCrop((oheight, owidth)),
transform.ToTensor(),
])(img)
sum2 = result.sum()
self.assertGreater(
sum2, 0,
f"height: {height} width: {width} oheight: {oheight} owdith: {owidth}"
)
self.assertGreaterEqual(
sum2, sum1,
f"height: {height} width: {width} oheight: {oheight} owdith: {owidth}"
)
def test_random_choice(self):
random_state = random.getstate()
random.seed(42)
random_choice_transform = transform.RandomChoice([
transform.Resize(15),
transform.Resize(20),
transform.CenterCrop(10)
])
img = transform.ToPILImage()(jt.random((25, 25, 3)))
num_samples = 250
num_resize_15 = 0
num_resize_20 = 0
num_crop_10 = 0
for _ in range(num_samples):
out = random_choice_transform(img)
if out.size == (15, 15):
num_resize_15 += 1
elif out.size == (20, 20):
num_resize_20 += 1
elif out.size == (10, 10):
num_crop_10 += 1
p_value = stats.binom_test(num_resize_15, num_samples, p=0.33333)
self.assertGreater(p_value, 0.0001)
p_value = stats.binom_test(num_resize_20, num_samples, p=0.33333)
self.assertGreater(p_value, 0.0001)
p_value = stats.binom_test(num_crop_10, num_samples, p=0.33333)
self.assertGreater(p_value, 0.0001)
random.setstate(random_state)
def test_random_order(self):
random_state = random.getstate()
random.seed(42)
random_order_transform = transform.RandomOrder(
[transform.Resize(20),
transform.CenterCrop(10)])
img = transform.ToPILImage()(jt.random((3, 25, 25)))
num_samples = 250
num_normal_order = 0
resize_crop_out = transform.CenterCrop(10)(transform.Resize(20)(img))
for _ in range(num_samples):
out = random_order_transform(img)
if out == resize_crop_out:
num_normal_order += 1
p_value = stats.binom_test(num_normal_order, num_samples, p=0.5)
random.setstate(random_state)
self.assertGreater(p_value, 0.0001)
def transform(self, img, hflip=False):
if self.crop is not None:
if isinstance(self.crop, int):
img = tfs.CenterCrop(self.crop)(img)
else:
assert len(self.crop) == 4, 'Crop size must be an integer for center crop, or a list of 4 integers (y0,x0,h,w)'
img = tfs.crop(img, *self.crop)
img = tfs.resize(img, (self.image_size, self.image_size))
if hflip:
img = tfs.hflip(img)
return tfs.to_tensor(img)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--batch_size', type=int, default=8)
parser.add_argument('--epochs', type=int, default=50)
parser.add_argument('--num_classes', type=int, default=130)
parser.add_argument('--lr', type=float, default=2e-3)
parser.add_argument('--weight_decay', type=float, default=1e-5)
parser.add_argument('--resume', type=bool, default=True)
parser.add_argument('--eval', type=bool, default=False)
parser.add_argument('--dataroot',
type=str,
default='/content/drive/MyDrive/dogfl/data/TEST_A/')
parser.add_argument('--model_path', type=str, default='./best_model.bin')
parser.add_argument('--out_file', type=str, default='./result.json')
args = parser.parse_args()
root_dir = args.dataroot
transform_test = transform.Compose([
transform.Resize((512, 512)),
transform.CenterCrop(448),
transform.ToTensor(),
transform.ImageNormalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
])
name_list = []
for _, _, _name_list in os.walk(root_dir):
name_list = _name_list
val_loader = TsinghuaDogExam(root_dir,
batch_size=args.batch_size,
train=False,
name_list=name_list,
shuffle=False,
transform=transform_test)
model = Net(num_classes=args.num_classes)
if args.resume:
model.load(args.model_path)
print('model loaded', args.model_path)
top5_class_list = evaluate(model, val_loader)
# label start from 1, however it doesn't
pred_result = dict(zip(name_list, top5_class_list))
with open(args.out_file, 'w') as fout:
json.dump(pred_result, fout, ensure_ascii=False, indent=4)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--batch_size', type=int, default=8)
parser.add_argument('--epochs', type=int, default=50)
parser.add_argument('--num_classes', type=int, default=130)
parser.add_argument('--lr', type=float, default=2e-3)
parser.add_argument('--weight_decay', type=float, default=1e-5)
parser.add_argument('--resume', type=bool, default=False)
parser.add_argument('--eval', type=bool, default=False)
parser.add_argument('--dataroot', type=str, default='/home/gmh/dataset/TsinghuaDog/')
parser.add_argument('--model_path', type=str, default='./best_model.pkl')
args = parser.parse_args()
transform_train = transform.Compose([
transform.Resize((512, 512)),
transform.RandomCrop(448),
transform.RandomHorizontalFlip(),
transform.ToTensor(),
transform.ImageNormalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
])
root_dir = args.dataroot
train_loader = TsinghuaDog(root_dir, batch_size=16, train=True, part='train', shuffle=True, transform=transform_train)
transform_test = transform.Compose([
transform.Resize((512, 512)),
transform.CenterCrop(448),
transform.ToTensor(),
transform.ImageNormalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
])
val_loader = TsinghuaDog(root_dir, batch_size=16, train=False, part='val', shuffle=False, transform=transform_test)
epochs = args.epochs
model = Net(num_classes=args.num_classes)
lr = args.lr
weight_decay = args.weight_decay
optimizer = SGD(model.parameters(), lr=lr, momentum=0.9)
if args.resume:
model.load(args.model_path)
if args.eval:
evaluate(model, val_loader)
return
for epoch in range(epochs):
train(model, train_loader, optimizer, epoch)
evaluate(model, val_loader, epoch)
def transforms_imagenet_eval(img_size=224,
crop_pct=0.9,
interpolation=Image.BICUBIC,
mean=(0.485, 0.456, 0.406),
std=(0.229, 0.224, 0.225)):
crop_pct = crop_pct or 0.875
if isinstance(img_size, tuple):
assert len(img_size) == 2
if img_size[-1] == img_size[-2]:
# fall-back to older behaviour so Resize scales to shortest edge if target is square
scale_size = int(math.floor(img_size[0] / crop_pct))
else:
scale_size = tuple([int(x / crop_pct) for x in img_size])
else:
scale_size = int(math.floor(img_size / crop_pct))
return transforms.Compose([
Resize(scale_size, interpolation),
transforms.CenterCrop(img_size),
transforms.ToTensor(),
transforms.ImageNormalize(mean=mean, std=std)
])
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--batch_size', type=int, default=8)
parser.add_argument('--epochs', type=int, default=50)
parser.add_argument('--num_classes', type=int, default=130)
parser.add_argument('--lr', type=float, default=2e-3)
parser.add_argument('--weight_decay', type=float, default=1e-5)
parser.add_argument('--resume', type=bool, default=True)
parser.add_argument('--eval', type=bool, default=False)
parser.add_argument('--dataroot', type=str, default='/content/drive/MyDrive/dogfl/data/TEST_A/')
parser.add_argument('--model_path', type=str, default='model/res152_8/model.bin:model/res152_10/model.bin:model/seres152_8/model.bin:model/seres152_10/model.bin')
parser.add_argument('--model_name', type=str, default='Net1_z:Net1_z:Net10_z:Net10_z')
parser.add_argument('--out_file', type=str, default='./result.json')
args = parser.parse_args()
root_dir = args.dataroot
transform_test = transform.Compose([
transform.Resize((256, 256)),
transform.CenterCrop(224),
transform.ToTensor(),
transform.ImageNormalize(0.485, 0.229),
])
model_zoo = args.model_path.split(':')
model_name_class = args.model_name.split(':')
print(model_zoo, model_name_class)
zoo_pred_result = []
i = 0
for model_path_ in model_zoo:
name_list = []
for _, _, _name_list in os.walk(root_dir):
name_list = _name_list
val_loader = TsinghuaDogExam(root_dir, batch_size=args.batch_size, train=False, name_list=name_list, shuffle=False, transform=transform_test)
model = eval(model_name_class[i])(num_classes=args.num_classes)
if args.resume:
model.load(model_path_)
top5_class_list = evaluate(model, val_loader)
# label start from 1, however it doesn't
pred_result = dict(zip(name_list, top5_class_list))
zoo_pred_result.append(pred_result)
i += 1
# vote the best
president = zoo_pred_result[0]
vote_result = {}
for key in president.keys():
val_list = []
for i in range(5):
candiates = [model[key][i] for model in zoo_pred_result]
val, n = Counter(candiates).most_common()[0]
val_list.append(val)
vote_result[key] = val_list
with open(args.out_file, 'w') as fout:
json.dump(vote_result, fout, ensure_ascii=False, indent=4)