def valid():
transforms = T.Compose(
[T.Resize((256, 256)),
T.CenterCrop(224),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])],
to_rgb=True)
peach_test = DemoDataset(transforms, mode='test')
model = hub.Module(name='resnet50_vd_imagenet_ssld', label_list=["R0", "B1", "M2", "S3"])
optimizer = paddle.optimizer.Adam(learning_rate=0.001, parameters=model.parameters())
trainer = Trainer(model, optimizer, checkpoint_dir='img_classification_ckpt', use_gpu=True)
trainer.evaluate(peach_test, 16)
import paddle
import paddlehub as hub
import paddlehub.vision.transforms as T
from paddlehub.finetune.trainer import Trainer
from paddlehub.datasets import Flowers
if __name__ == '__main__':
transforms = T.Compose(
[T.Resize((256, 256)),
T.CenterCrop(224),
T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])],
to_rgb=True)
flowers = Flowers(transforms)
flowers_validate = Flowers(transforms, mode='val')
model = hub.Module(
name='resnet50_vd_imagenet_ssld',
label_list=["roses", "tulips", "daisy", "sunflowers", "dandelion"],
load_checkpoint=None)
optimizer = paddle.optimizer.Adam(learning_rate=0.001, parameters=model.parameters())
trainer = Trainer(model, optimizer, checkpoint_dir='img_classification_ckpt', use_gpu=True)
trainer.train(flowers, epochs=100, batch_size=32, eval_dataset=flowers_validate, save_interval=10)
if __name__ == "__main__":
train_transforms = Compose([Resize(target_size=(512, 512)), Normalize()])
eval_transforms = Compose([Normalize()])
train_reader = OpticDiscSeg(train_transforms)
eval_reader = OpticDiscSeg(eval_transforms, mode='val')
model = hub.Module(name='ocrnet_hrnetw18_voc', num_classes=2)
scheduler = paddle.optimizer.lr.PolynomialDecay(learning_rate=0.01,
decay_steps=1000,
power=0.9,
end_lr=0.0001)
optimizer = paddle.optimizer.Momentum(learning_rate=scheduler,
parameters=model.parameters())
trainer = Trainer(model,
optimizer,
checkpoint_dir='test_ckpt_img_seg',
use_gpu=True)
trainer.train(train_reader,
epochs=10,
batch_size=4,
log_interval=10,
save_interval=4)
cfm = ConfusionMatrix(eval_reader.num_classes, streaming=True)
model.eval()
for imgs, labels in eval_reader:
imgs = imgs[np.newaxis, :, :, :]
preds = model(paddle.to_tensor(imgs))[0]
preds = paddle.argmax(preds, axis=1, keepdim=True).numpy()
labels = labels[np.newaxis, :, :, :]
ignores = labels != eval_reader.ignore_index
import paddle
import paddlehub as hub
from paddlehub.finetune.trainer import Trainer
from paddlehub.datasets.minicoco import MiniCOCO
import paddlehub.vision.transforms as T
if __name__ == "__main__":
model = hub.Module(name='msgnet')
transform = T.Compose([T.Resize((256, 256), interpolation='LINEAR')])
styledata = MiniCOCO(transform)
optimizer = paddle.optimizer.Adam(learning_rate=0.0001,
parameters=model.parameters())
trainer = Trainer(model, optimizer, checkpoint_dir='test_style_ckpt')
trainer.train(styledata,
epochs=101,
batch_size=4,
eval_dataset=styledata,
log_interval=10,
save_interval=10)
import paddle
import paddlehub as hub
import paddlehub.vision.transforms as T
from paddlehub.finetune.trainer import Trainer
from paddlehub.datasets import Canvas
if __name__ == '__main__':
transform = T.Compose(
[T.Resize((256, 256), interpolation='NEAREST'),
T.RandomPaddingCrop(crop_size=176),
T.RGB2LAB()], to_rgb=True)
color_set = Canvas(transform=transform, mode='train')
model = hub.Module(name='user_guided_colorization', load_checkpoint='/PATH/TO/CHECKPOINT')
model.set_config(classification=True, prob=1)
optimizer = paddle.optimizer.Adam(learning_rate=0.0001, parameters=model.parameters())
trainer = Trainer(model, optimizer, checkpoint_dir='img_colorization_ckpt_cls_1')
trainer.train(color_set, epochs=201, batch_size=25, eval_dataset=color_set, log_interval=10, save_interval=10)
model.set_config(classification=False, prob=0.125)
optimizer = paddle.optimizer.Adam(learning_rate=0.00001, parameters=model.parameters())
trainer = Trainer(model, optimizer, checkpoint_dir='img_colorization_ckpt_reg_1')
trainer.train(color_set, epochs=101, batch_size=25, log_interval=10, save_interval=10)