def from_pretrained(cls, model_name, num_classes, dropout_rate=0.0):
model = cls.from_name(model_name,
num_classes=num_classes,
dropout_rate=dropout_rate)
print(model._global_params.dropout_rate)
load_pretrained_weights(model, model_name, False)
return model
def from_pretrained(cls, model_name, num_classes=1000):
model = EfficientNet.from_name(
model_name, override_params={'num_classes': num_classes})
load_pretrained_weights(model,
model_name,
load_fc=(num_classes == 1000))
return model
def from_pretrained(cls, model_name, advprop=False, num_classes=1000, in_channels=3):
model = cls.from_name(model_name, override_params={'num_classes': num_classes})
load_pretrained_weights(model, model_name, load_fc=(num_classes == 1000), advprop=advprop)
if in_channels != 3:
Conv2d = get_same_padding_conv2d(image_size=model._global_params.image_size)
out_channels = round_filters(32, model._global_params)
model._conv_stem = Conv2d(in_channels, out_channels, kernel_size=3, stride=2, bias=False)
return model
def from_pretrained(cls,
model_name,
advprop=False,
num_classes=2,
in_channels=3):
model = cls.from_name(model_name,
override_params={'num_classes': num_classes})
load_pretrained_weights(model,
model_name,
load_fc=(num_classes == 1000),
advprop=advprop)
model._change_in_channels(in_channels)
return model
import torch
def from_pretrained(cls, model_name, override_params=None, **kways):
model = EfficientNet_encoder.from_name(model_name, override_params,
**kways)
load_pretrained_weights(model, model_name, load_fc=False)
return model
def __init__(self, model_name='efficientnet-b0'):
blocks_args, global_params = get_model_params(model_name, override_params={})
super().__init__(blocks_args, global_params)
load_pretrained_weights(self, model_name=model_name, load_fc=True)
self.model_name = model_name
