def recordDense(info):
global SKIP
import torchvision.models.densenet as denGen
if not (SKIP and 'densenet121' in info['name_list']):
INFO("proceeding for DenseNet121")
net = denGen.densenet121(pretrained=True).cuda()
sum = __summary(net, [3, 224, 224], verbose=True)
__writeInfoJSON(sum, 'densenet121')
else:
INFO("Skip DenseNet121")
if not (SKIP and 'densenet161' in info['name_list']):
INFO("proceeding for DenseNet161")
net = denGen.densenet161(pretrained=True).cuda()
sum = __summary(net, [3, 224, 224], verbose=True)
__writeInfoJSON(sum, 'densenet161')
else:
INFO("Skip DenseNet161")
if not (SKIP and 'densenet169' in info['name_list']):
INFO("proceeding for DenseNet169")
net = denGen.densenet169(pretrained=True).cuda()
sum = __summary(net, [3, 224, 224], verbose=True)
__writeInfoJSON(sum, 'densenet169')
else:
INFO("Skip DenseNet169")
if not (SKIP and 'densenet201' in info['name_list']):
INFO("proceeding for DenseNet201")
net = denGen.densenet201(pretrained=True).cuda()
sum = __summary(net, [3, 224, 224], verbose=True)
__writeInfoJSON(sum, 'densenet201')
else:
INFO("Skip DenseNet201")
def __init__(self,
subtype='densenet121',
out_stages=[2, 3, 4],
backbone_path=None):
super(Densenet, self).__init__()
self.out_stages = out_stages
self.backbone_path = backbone_path
self.out_channels = [64, 128, 256, 512, 1024]
if subtype == 'densenet121':
features = densenet121(pretrained=not backbone_path).features
elif subtype == 'densenet161':
features = densenet161(pretrained=not backbone_path).features
elif subtype == 'densenet169':
features = densenet169(pretrained=not backbone_path).features
elif subtype == 'densenet201':
features = densenet201(pretrained=not backbone_path).features
self.out_channels = self.out_channels[self.out_stages[0]:self.
out_stages[-1] + 1]
self.conv1 = nn.Sequential(features.conv0, features.norm0,
features.relu0, features.pool0)
self.layer1 = nn.Sequential(features.denseblock1, features.transition1)
self.layer2 = nn.Sequential(features.denseblock2, features.transition2)
self.layer3 = nn.Sequential(features.denseblock3, features.transition3)
self.layer4 = features.denseblock4
if self.backbone_path:
self.features.load_state_dict(torch.load(self.backbone_path))
else:
self.init_weights()
def __init__(self,
cf,
num_classes=21,
pretrained=False,
net_name='densenet161'):
super(DenseNet161, self).__init__(cf)
self.url = ''
self.pretrained = pretrained
self.net_name = net_name
if pretrained:
self.model = models.densenet161(pretrained=True)
self.model.classifier = nn.Linear(1024, num_classes)
else:
self.model = models.densenet161(pretrained=False,
num_classes=num_classes)
def __init__(self, config):
super().__init__(config)
self.freeze_num = 2
feats = densenet.densenet161(
num_classes=1000, pretrained="imagenet").children().__next__()
self.model = nn.Sequential(*list(feats.children())[:-2])
self.dropout = nn.Dropout2d(p=0.2)
self.get_last_linear(in_features=1056)
def __init__(self,
cf,
num_classes=21,
pretrained=False,
net_name='densenet161'):
super(DenseNet161, self).__init__(cf)
self.pretrained = pretrained
self.net_name = net_name
if self.pretrained:
self.model = models.densenet161(pretrained=True)
num_ftrs = self.model.classifier.in_features
self.model.classifier = nn.Linear(num_ftrs, num_classes)
self.model = models.densenet161(pretrained=False,
num_classes=num_classes)
'''if pretrained:
def create_model(model_name, num_classes=1000, pretrained=False, **kwargs):
if 'test_time_pool' in kwargs:
test_time_pool = kwargs.pop('test_time_pool')
else:
test_time_pool = True
if 'extra' in kwargs:
extra = kwargs.pop('extra')
else:
extra = True
if model_name == 'dpn68':
model = dpn68(
num_classes=num_classes, pretrained=pretrained, test_time_pool=test_time_pool)
elif model_name == 'dpn68b':
model = dpn68b(
num_classes=num_classes, pretrained=pretrained, test_time_pool=test_time_pool)
elif model_name == 'dpn92':
model = dpn92(
num_classes=num_classes, pretrained=pretrained, test_time_pool=test_time_pool, extra=extra)
elif model_name == 'dpn98':
model = dpn98(
num_classes=num_classes, pretrained=pretrained, test_time_pool=test_time_pool)
elif model_name == 'dpn131':
model = dpn131(
num_classes=num_classes, pretrained=pretrained, test_time_pool=test_time_pool)
elif model_name == 'dpn107':
model = dpn107(
num_classes=num_classes, pretrained=pretrained, test_time_pool=test_time_pool)
elif model_name == 'resnet18':
model = resnet18(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'resnet34':
model = resnet34(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'resnet50':
model = resnet50(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'resnet101':
model = resnet101(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'resnet152':
model = resnet152(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'densenet121':
model = densenet121(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'densenet161':
model = densenet161(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'densenet169':
model = densenet169(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'densenet201':
model = densenet201(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'inception_v3':
model = inception_v3(
num_classes=num_classes, pretrained=pretrained, transform_input=False, **kwargs)
else:
assert False, "Unknown model architecture (%s)" % model_name
return model
def create_model(model_name, num_classes=1000, pretrained=False, **kwargs):
if 'test_time_pool' in kwargs:
test_time_pool = kwargs.pop('test_time_pool')
else:
test_time_pool = True
if 'extra' in kwargs:
extra = kwargs.pop('extra')
else:
extra = True
if model_name == 'dpn68':
model = dpn68(
num_classes=num_classes, pretrained=pretrained, test_time_pool=test_time_pool)
elif model_name == 'dpn68b':
model = dpn68b(
num_classes=num_classes, pretrained=pretrained, test_time_pool=test_time_pool)
elif model_name == 'dpn92':
model = dpn92(
num_classes=num_classes, pretrained=pretrained, test_time_pool=test_time_pool, extra=extra)
elif model_name == 'dpn98':
model = dpn98(
num_classes=num_classes, pretrained=pretrained, test_time_pool=test_time_pool)
elif model_name == 'dpn131':
model = dpn131(
num_classes=num_classes, pretrained=pretrained, test_time_pool=test_time_pool)
elif model_name == 'dpn107':
model = dpn107(
num_classes=num_classes, pretrained=pretrained, test_time_pool=test_time_pool)
elif model_name == 'resnet18':
model = resnet18(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'resnet34':
model = resnet34(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'resnet50':
model = resnet50(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'resnet101':
model = resnet101(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'resnet152':
model = resnet152(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'densenet121':
model = densenet121(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'densenet161':
model = densenet161(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'densenet169':
model = densenet169(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'densenet201':
model = densenet201(num_classes=num_classes, pretrained=pretrained, **kwargs)
elif model_name == 'inception_v3':
model = inception_v3(
num_classes=num_classes, pretrained=pretrained, transform_input=False, **kwargs)
else:
assert False, "Unknown model architecture (%s)" % model_name
return model
def get_densenet_model(densenet, num_classes=-1):
if densenet == "densenet121":
model = densenet121(pretrained=True)
elif densenet == "densenet169":
model = densenet169(pretrained=True)
elif densenet == "densenet201":
model = densenet201(pretrained=True)
elif densenet == "densenet161":
model = densenet161(pretrained=True)
else:
raise RuntimeError("Unsupported model, %s" % densenet)
if num_classes > 0:
in_features = model.classifier.in_features
classifier = nn.Linear(in_features, num_classes, bias=True)
model.classifier = classifier
return model
def __init__(self,
num_class=1000,
in_channels=3,
pretrained=False,
**kargs):
super(Densenet161, self).__init__()
self.model = densenet161(pretrained=pretrained)
self.model.features[0] = torch.nn.Conv2d(in_channels=in_channels,
out_channels=96,
kernel_size=7,
stride=2,
padding=3,
bias=False)
self.model.classifier = torch.nn.Linear(in_features=2208,
out_features=num_class,
bias=True)
def __init__(self, pretrained=True):
super(FurnitureDenseNet161_350, self).__init__()
self.model = densenet161(num_classes=1000, pretrained=pretrained)
num_features = self.model.classifier.in_features
self.model.classifier = Linear(num_features, 128)
for m in self.model.classifier.modules():
if isinstance(m, Linear):
m.weight.data.normal_(0, 0.01)
m.bias.data.zero_()
# create aliases:
self.stem = ModuleList([
self.model.features[0],
self.model.features[1],
])
self.features = ModuleList([
self.model.features[i] for i in range(2, len(self.model.features))
])
self.classifier = self.model.classifier
def __init__(self, pretrained=True, progress=True, **kwargs):
super(densenet161, self).__init__()
backbone = densenet.densenet161(pretrained, progress, **kwargs)
self.backbone = backbone.features
from collections import OrderedDict
# Project imports
from util.util import print # print with a header for this project
# Leveraged Torchvision implementation of DenseNet at:
# https://github.com/pytorch/vision/blob/master/torchvision/models/densenet.py
_use_pretrained = True
name_to_model_fns = {
"densenet121": lambda: densenet.densenet121(pretrained=_use_pretrained),
"densenet169": lambda: densenet.densenet169(pretrained=_use_pretrained),
"densenet201": lambda: densenet.densenet201(
pretrained=_use_pretrained) # We're just going to use this one
,
"densenet161": lambda: densenet.densenet161(pretrained=_use_pretrained)
}
def get_densenet(name):
return name_to_model_fns[name]() # Call the function
"""
old_model.modules is more accurate of all indiv. layers
old_model.features decomposes structure more, but doesn't include final FC classifier
(instead under old_model.classifier)
DenseNet201's model.features [nn.Sequential]
0 = conv2d
1 = batchnorm