def create_loss(out,
feeds,
architecture,
classes_num=1000,
epsilon=None,
use_mix=False,
use_distillation=False,
use_pure_fp16=False):
"""
Create a loss for optimization, such as:
1. CrossEnotry loss
2. CrossEnotry loss with label smoothing
3. CrossEnotry loss with mix(mixup, cutmix, fmix)
4. CrossEnotry loss with label smoothing and (mixup, cutmix, fmix)
5. GoogLeNet loss
Args:
out(variable): model output variable
feeds(dict): dict of model input variables
architecture(dict): architecture information,
name(such as ResNet50) is needed
classes_num(int): num of classes
epsilon(float): parameter for label smoothing, 0.0 <= epsilon <= 1.0
use_mix(bool): whether to use mix(include mixup, cutmix, fmix)
use_pure_fp16(bool): whether to use pure fp16 data as training parameter
Returns:
loss(variable): loss variable
"""
if use_mix:
feed_y_a = paddle.reshape(feeds['feed_y_a'], [-1, 1])
feed_y_b = paddle.reshape(feeds['feed_y_b'], [-1, 1])
feed_lam = paddle.reshape(feeds['feed_lam'], [-1, 1])
else:
target = paddle.reshape(feeds['label'], [-1, 1])
if architecture["name"] == "GoogLeNet":
assert len(out) == 3, "GoogLeNet should have 3 outputs"
loss = GoogLeNetLoss(class_dim=classes_num, epsilon=epsilon)
return loss(out[0], out[1], out[2], target)
if use_distillation:
assert len(out) == 2, ("distillation output length must be 2, "
"but got {}".format(len(out)))
loss = JSDivLoss(class_dim=classes_num, epsilon=epsilon)
return loss(out[1], out[0])
if use_mix:
loss = MixCELoss(class_dim=classes_num, epsilon=epsilon)
return loss(out, feed_y_a, feed_y_b, feed_lam, use_pure_fp16)
else:
loss = CELoss(class_dim=classes_num, epsilon=epsilon)
return loss(out, target, use_pure_fp16)
def create_loss(out,
feeds,
architecture,
classes_num=1000,
epsilon=None,
mix=False):
"""
Create a loss for optimization, such as:
1. CrossEnotry loss
2. CrossEnotry loss with label smoothing
3. CrossEnotry loss with mix(mixup, cutmix, fmix)
4. CrossEnotry loss with label smoothing and (mixup, cutmix, fmix)
5. GoogLeNet loss
Args:
out(variable): model output variable
feeds(dict): dict of model input variables
architecture(str): model name, such as ResNet50
classes_num(int): num of classes
epsilon(float): parameter for label smoothing, 0.0 <= epsilon <= 1.0
mix(bool): whether to use mix(include mixup, cutmix, fmix)
Returns:
loss(variable): loss variable
"""
if architecture == "GoogLeNet":
assert len(out) == 3, "GoogLeNet should have 3 outputs"
loss = GoogLeNetLoss(class_dim=classes_num, epsilon=epsilon)
target = feeds['label']
return loss(out[0], out[1], out[2], target)
if mix:
loss = MixCELoss(class_dim=classes_num, epsilon=epsilon)
feed_y_a = feeds['feed_y_a']
feed_y_b = feeds['feed_y_b']
feed_lam = feeds['feed_lam']
return loss(out, feed_y_a, feed_y_b, feed_lam)
else:
loss = CELoss(class_dim=classes_num, epsilon=epsilon)
target = feeds['label']
return loss(out, target)