diff --git a/timm/models/densenet.py b/timm/models/densenet.py
index b8e556db..dd144b70 100644
--- a/timm/models/densenet.py
+++ b/timm/models/densenet.py
@@ -43,7 +43,7 @@ def _filter_pretrained(state_dict):
     return state_dict
 
 
-def densenet121(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def densenet121(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     r"""Densenet-121 model from
     `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`
     """
@@ -56,7 +56,7 @@ def densenet121(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def densenet169(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def densenet169(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     r"""Densenet-169 model from
     `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`
     """
@@ -69,7 +69,7 @@ def densenet169(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def densenet201(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def densenet201(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     r"""Densenet-201 model from
     `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`
     """
@@ -82,7 +82,7 @@ def densenet201(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def densenet161(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def densenet161(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     r"""Densenet-201 model from
     `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`
     """
diff --git a/timm/models/dpn.py b/timm/models/dpn.py
index 04aa9a5c..636801e9 100644
--- a/timm/models/dpn.py
+++ b/timm/models/dpn.py
@@ -11,6 +11,7 @@ from __future__ import print_function
 
 import torch
 import torch.nn as nn
+import torch.nn.functional as F
 from collections import OrderedDict
 
 from .helpers import load_pretrained
@@ -31,81 +32,87 @@ def _cfg(url=''):
 
 
 default_cfgs = {
-    'dpn68': _cfg(url='http://data.lip6.fr/cadene/pretrainedmodels/dpn68-66bebafa7.pth'),
-    'dpn68b_extra': _cfg(url='http://data.lip6.fr/cadene/pretrainedmodels/dpn68b_extra-84854c156.pth'),
-    'dpn92_extra': _cfg(url='http://data.lip6.fr/cadene/pretrainedmodels/dpn92_extra-b040e4a9b.pth'),
-    'dpn98': _cfg(url='http://data.lip6.fr/cadene/pretrainedmodels/dpn98-5b90dec4d.pth'),
-    'dpn131': _cfg(url='http://data.lip6.fr/cadene/pretrainedmodels/dpn131-71dfe43e0.pth'),
-    'dpn107_extra': _cfg(url='http://data.lip6.fr/cadene/pretrainedmodels/dpn107_extra-1ac7121e2.pth')
+    'dpn68': _cfg(
+        url='https://github.com/rwightman/pytorch-dpn-pretrained/releases/download/v0.1/dpn68-66bebafa7.pth'),
+    'dpn68b_extra': _cfg(
+        url='https://github.com/rwightman/pytorch-dpn-pretrained/releases/download/v0.1/dpn68b_extra-84854c156.pth'),
+    'dpn92_extra': _cfg(
+        url='https://github.com/rwightman/pytorch-dpn-pretrained/releases/download/v0.1/dpn92_extra-b040e4a9b.pth'),
+    'dpn98': _cfg(
+        url='https://github.com/rwightman/pytorch-dpn-pretrained/releases/download/v0.1/dpn98-5b90dec4d.pth'),
+    'dpn131': _cfg(
+        url='https://github.com/rwightman/pytorch-dpn-pretrained/releases/download/v0.1/dpn131-71dfe43e0.pth'),
+    'dpn107_extra': _cfg(
+        url='https://github.com/rwightman/pytorch-dpn-pretrained/releases/download/v0.1/dpn107_extra-1ac7121e2.pth')
 }
 
 
-def dpn68(num_classes=1000, in_chans=3, pretrained=False):
+def dpn68(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['dpn68']
     model = DPN(
         small=True, num_init_features=10, k_r=128, groups=32,
         k_sec=(3, 4, 12, 3), inc_sec=(16, 32, 32, 64),
-        num_classes=num_classes, in_chans=in_chans)
+        num_classes=num_classes, in_chans=in_chans, **kwargs)
     model.default_cfg = default_cfg
     if pretrained:
         load_pretrained(model, default_cfg, num_classes, in_chans)
     return model
 
 
-def dpn68b(num_classes=1000, in_chans=3, pretrained=False):
+def dpn68b(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['dpn68b_extra']
     model = DPN(
         small=True, num_init_features=10, k_r=128, groups=32,
         b=True, k_sec=(3, 4, 12, 3), inc_sec=(16, 32, 32, 64),
-        num_classes=num_classes, in_chans=in_chans)
+        num_classes=num_classes, in_chans=in_chans, **kwargs)
     model.default_cfg = default_cfg
     if pretrained:
         load_pretrained(model, default_cfg, num_classes, in_chans)
     return model
 
 
-def dpn92(num_classes=1000, in_chans=3, pretrained=False):
+def dpn92(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['dpn92_extra']
     model = DPN(
         num_init_features=64, k_r=96, groups=32,
         k_sec=(3, 4, 20, 3), inc_sec=(16, 32, 24, 128),
-        num_classes=num_classes, in_chans=in_chans)
+        num_classes=num_classes, in_chans=in_chans, **kwargs)
     model.default_cfg = default_cfg
     if pretrained:
         load_pretrained(model, default_cfg, num_classes, in_chans)
     return model
 
 
-def dpn98(num_classes=1000, in_chans=3, pretrained=False):
+def dpn98(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['dpn98']
     model = DPN(
         num_init_features=96, k_r=160, groups=40,
         k_sec=(3, 6, 20, 3), inc_sec=(16, 32, 32, 128),
-        num_classes=num_classes, in_chans=in_chans)
+        num_classes=num_classes, in_chans=in_chans, **kwargs)
     model.default_cfg = default_cfg
     if pretrained:
         load_pretrained(model, default_cfg, num_classes, in_chans)
     return model
 
 
-def dpn131(num_classes=1000, in_chans=3, pretrained=False):
+def dpn131(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['dpn131']
     model = DPN(
         num_init_features=128, k_r=160, groups=40,
         k_sec=(4, 8, 28, 3), inc_sec=(16, 32, 32, 128),
-        num_classes=num_classes, in_chans=in_chans)
+        num_classes=num_classes, in_chans=in_chans, **kwargs)
     model.default_cfg = default_cfg
     if pretrained:
         load_pretrained(model, default_cfg, num_classes, in_chans)
     return model
 
 
-def dpn107(num_classes=1000, in_chans=3, pretrained=False):
+def dpn107(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['dpn107_extra']
     model = DPN(
         num_init_features=128, k_r=200, groups=50,
         k_sec=(4, 8, 20, 3), inc_sec=(20, 64, 64, 128),
-        num_classes=num_classes, in_chans=in_chans)
+        num_classes=num_classes, in_chans=in_chans, **kwargs)
     model.default_cfg = default_cfg
     if pretrained:
         load_pretrained(model, default_cfg, num_classes, in_chans)
@@ -220,9 +227,11 @@ class DualPathBlock(nn.Module):
 class DPN(nn.Module):
     def __init__(self, small=False, num_init_features=64, k_r=96, groups=32,
                  b=False, k_sec=(3, 4, 20, 3), inc_sec=(16, 32, 24, 128),
-                 num_classes=1000, in_chans=3, fc_act=nn.ELU(inplace=True)):
+                 num_classes=1000, in_chans=3, drop_rate=0., global_pool='avg', fc_act=nn.ELU()):
         super(DPN, self).__init__()
         self.num_classes = num_classes
+        self.drop_rate = drop_rate
+        self.global_pool = global_pool
         self.b = b
         bw_factor = 1 if small else 4
 
@@ -285,8 +294,9 @@ class DPN(nn.Module):
     def get_classifier(self):
         return self.classifier
 
-    def reset_classifier(self, num_classes):
+    def reset_classifier(self, num_classes, global_pool='avg'):
         self.num_classes = num_classes
+        self.global_pool = global_pool
         del self.classifier
         if num_classes:
             self.classifier = nn.Conv2d(self.num_features, num_classes, kernel_size=1, bias=True)
@@ -296,11 +306,13 @@ class DPN(nn.Module):
     def forward_features(self, x, pool=True):
         x = self.features(x)
         if pool:
-            x = select_adaptive_pool2d(x, pool_type='avg')
+            x = select_adaptive_pool2d(x, pool_type=self.global_pool)
         return x
 
     def forward(self, x):
         x = self.forward_features(x)
+        if self.drop_rate > 0.:
+            x = F.dropout(x, p=self.drop_rate, training=self.training)
         out = self.classifier(x)
         return out.view(out.size(0), -1)
 
diff --git a/timm/models/gen_efficientnet.py b/timm/models/gen_efficientnet.py
index 06f59bcf..1feee809 100644
--- a/timm/models/gen_efficientnet.py
+++ b/timm/models/gen_efficientnet.py
@@ -1157,7 +1157,7 @@ def _gen_efficientnet(channel_multiplier=1.0, depth_multiplier=1.0, num_classes=
     return model
 
 
-def mnasnet_050(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def mnasnet_050(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MNASNet B1, depth multiplier of 0.5. """
     default_cfg = default_cfgs['mnasnet_050']
     model = _gen_mnasnet_b1(0.5, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1167,7 +1167,7 @@ def mnasnet_050(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def mnasnet_075(num_classes, in_chans=3, pretrained=False, **kwargs):
+def mnasnet_075(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MNASNet B1, depth multiplier of 0.75. """
     default_cfg = default_cfgs['mnasnet_075']
     model = _gen_mnasnet_b1(0.75, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1177,7 +1177,7 @@ def mnasnet_075(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def mnasnet_100(num_classes, in_chans=3, pretrained=False, **kwargs):
+def mnasnet_100(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MNASNet B1, depth multiplier of 1.0. """
     default_cfg = default_cfgs['mnasnet_100']
     model = _gen_mnasnet_b1(1.0, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1187,12 +1187,12 @@ def mnasnet_100(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def mnasnet_b1(num_classes, in_chans=3, pretrained=False, **kwargs):
+def mnasnet_b1(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MNASNet B1, depth multiplier of 1.0. """
     return mnasnet_100(num_classes, in_chans, pretrained, **kwargs)
 
 
-def tflite_mnasnet_100(num_classes, in_chans=3, pretrained=False, **kwargs):
+def tflite_mnasnet_100(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MNASNet B1, depth multiplier of 1.0. """
     default_cfg = default_cfgs['tflite_mnasnet_100']
     # these two args are for compat with tflite pretrained weights
@@ -1205,7 +1205,7 @@ def tflite_mnasnet_100(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def mnasnet_140(num_classes, in_chans=3, pretrained=False, **kwargs):
+def mnasnet_140(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MNASNet B1,  depth multiplier of 1.4 """
     default_cfg = default_cfgs['mnasnet_140']
     model = _gen_mnasnet_b1(1.4, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1215,7 +1215,7 @@ def mnasnet_140(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def semnasnet_050(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def semnasnet_050(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MNASNet A1 (w/ SE), depth multiplier of 0.5 """
     default_cfg = default_cfgs['semnasnet_050']
     model = _gen_mnasnet_a1(0.5, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1225,7 +1225,7 @@ def semnasnet_050(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def semnasnet_075(num_classes, in_chans=3, pretrained=False, **kwargs):
+def semnasnet_075(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MNASNet A1 (w/ SE),  depth multiplier of 0.75. """
     default_cfg = default_cfgs['semnasnet_075']
     model = _gen_mnasnet_a1(0.75, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1235,7 +1235,7 @@ def semnasnet_075(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def semnasnet_100(num_classes, in_chans=3, pretrained=False, **kwargs):
+def semnasnet_100(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MNASNet A1 (w/ SE), depth multiplier of 1.0. """
     default_cfg = default_cfgs['semnasnet_100']
     model = _gen_mnasnet_a1(1.0, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1245,12 +1245,12 @@ def semnasnet_100(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def mnasnet_a1(num_classes, in_chans=3, pretrained=False, **kwargs):
+def mnasnet_a1(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MNASNet A1 (w/ SE), depth multiplier of 1.0. """
     return semnasnet_100(num_classes, in_chans, pretrained, **kwargs)
 
 
-def tflite_semnasnet_100(num_classes, in_chans=3, pretrained=False, **kwargs):
+def tflite_semnasnet_100(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MNASNet A1, depth multiplier of 1.0. """
     default_cfg = default_cfgs['tflite_semnasnet_100']
     # these two args are for compat with tflite pretrained weights
@@ -1263,7 +1263,7 @@ def tflite_semnasnet_100(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def semnasnet_140(num_classes, in_chans=3, pretrained=False, **kwargs):
+def semnasnet_140(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MNASNet A1 (w/ SE), depth multiplier of 1.4. """
     default_cfg = default_cfgs['semnasnet_140']
     model = _gen_mnasnet_a1(1.4, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1273,7 +1273,7 @@ def semnasnet_140(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def mnasnet_small(num_classes, in_chans=3, pretrained=False, **kwargs):
+def mnasnet_small(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MNASNet Small,  depth multiplier of 1.0. """
     default_cfg = default_cfgs['mnasnet_small']
     model = _gen_mnasnet_small(1.0, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1283,7 +1283,7 @@ def mnasnet_small(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def mobilenetv1_100(num_classes, in_chans=3, pretrained=False, **kwargs):
+def mobilenetv1_100(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MobileNet V1 """
     default_cfg = default_cfgs['mobilenetv1_100']
     model = _gen_mobilenet_v1(1.0, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1293,7 +1293,7 @@ def mobilenetv1_100(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def mobilenetv2_100(num_classes, in_chans=3, pretrained=False, **kwargs):
+def mobilenetv2_100(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MobileNet V2 """
     default_cfg = default_cfgs['mobilenetv2_100']
     model = _gen_mobilenet_v2(1.0, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1303,7 +1303,7 @@ def mobilenetv2_100(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def mobilenetv3_050(num_classes, in_chans=3, pretrained=False, **kwargs):
+def mobilenetv3_050(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MobileNet V3 """
     default_cfg = default_cfgs['mobilenetv3_050']
     model = _gen_mobilenet_v3(0.5, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1313,7 +1313,7 @@ def mobilenetv3_050(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def mobilenetv3_075(num_classes, in_chans=3, pretrained=False, **kwargs):
+def mobilenetv3_075(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MobileNet V3 """
     default_cfg = default_cfgs['mobilenetv3_075']
     model = _gen_mobilenet_v3(0.75, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1323,7 +1323,7 @@ def mobilenetv3_075(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def mobilenetv3_100(num_classes, in_chans=3, pretrained=False, **kwargs):
+def mobilenetv3_100(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ MobileNet V3 """
     default_cfg = default_cfgs['mobilenetv3_100']
     if pretrained:
@@ -1336,7 +1336,7 @@ def mobilenetv3_100(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def fbnetc_100(num_classes, in_chans=3, pretrained=False, **kwargs):
+def fbnetc_100(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ FBNet-C """
     default_cfg = default_cfgs['fbnetc_100']
     if pretrained:
@@ -1349,7 +1349,7 @@ def fbnetc_100(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def chamnetv1_100(num_classes, in_chans=3, pretrained=False, **kwargs):
+def chamnetv1_100(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ ChamNet """
     default_cfg = default_cfgs['chamnetv1_100']
     model = _gen_chamnet_v1(1.0, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1359,7 +1359,7 @@ def chamnetv1_100(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def chamnetv2_100(num_classes, in_chans=3, pretrained=False, **kwargs):
+def chamnetv2_100(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ ChamNet """
     default_cfg = default_cfgs['chamnetv2_100']
     model = _gen_chamnet_v2(1.0, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1369,7 +1369,7 @@ def chamnetv2_100(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def spnasnet_100(num_classes, in_chans=3, pretrained=False, **kwargs):
+def spnasnet_100(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ Single-Path NAS Pixel1"""
     default_cfg = default_cfgs['spnasnet_100']
     model = _gen_spnasnet(1.0, num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -1379,7 +1379,7 @@ def spnasnet_100(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def efficientnet_b0(num_classes, in_chans=3, pretrained=False, **kwargs):
+def efficientnet_b0(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ EfficientNet-B0 """
     default_cfg = default_cfgs['efficientnet_b0']
     # NOTE for train, drop_rate should be 0.2
@@ -1392,7 +1392,7 @@ def efficientnet_b0(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def efficientnet_b1(num_classes, in_chans=3, pretrained=False, **kwargs):
+def efficientnet_b1(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ EfficientNet-B1 """
     default_cfg = default_cfgs['efficientnet_b1']
     # NOTE for train, drop_rate should be 0.2
@@ -1405,7 +1405,7 @@ def efficientnet_b1(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def efficientnet_b2(num_classes, in_chans=3, pretrained=False, **kwargs):
+def efficientnet_b2(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ EfficientNet-B2 """
     default_cfg = default_cfgs['efficientnet_b2']
     # NOTE for train, drop_rate should be 0.3
@@ -1418,7 +1418,7 @@ def efficientnet_b2(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def efficientnet_b3(num_classes, in_chans=3, pretrained=False, **kwargs):
+def efficientnet_b3(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ EfficientNet-B3 """
     default_cfg = default_cfgs['efficientnet_b3']
     # NOTE for train, drop_rate should be 0.3
@@ -1431,7 +1431,7 @@ def efficientnet_b3(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def efficientnet_b4(num_classes, in_chans=3, pretrained=False, **kwargs):
+def efficientnet_b4(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ EfficientNet-B4 """
     default_cfg = default_cfgs['efficientnet_b4']
     # NOTE for train, drop_rate should be 0.4
@@ -1444,7 +1444,7 @@ def efficientnet_b4(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def efficientnet_b5(num_classes, in_chans=3, pretrained=False, **kwargs):
+def efficientnet_b5(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ EfficientNet-B5 """
     # NOTE for train, drop_rate should be 0.4
     default_cfg = default_cfgs['efficientnet_b5']
@@ -1457,7 +1457,7 @@ def efficientnet_b5(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def tf_efficientnet_b0(num_classes, in_chans=3, pretrained=False, **kwargs):
+def tf_efficientnet_b0(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ EfficientNet-B0. Tensorflow compatible variant  """
     default_cfg = default_cfgs['tf_efficientnet_b0']
     kwargs['bn_eps'] = _BN_EPS_TF_DEFAULT
@@ -1471,7 +1471,7 @@ def tf_efficientnet_b0(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def tf_efficientnet_b1(num_classes, in_chans=3, pretrained=False, **kwargs):
+def tf_efficientnet_b1(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ EfficientNet-B1. Tensorflow compatible variant  """
     default_cfg = default_cfgs['tf_efficientnet_b1']
     kwargs['bn_eps'] = _BN_EPS_TF_DEFAULT
@@ -1485,7 +1485,7 @@ def tf_efficientnet_b1(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def tf_efficientnet_b2(num_classes, in_chans=3, pretrained=False, **kwargs):
+def tf_efficientnet_b2(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ EfficientNet-B2. Tensorflow compatible variant  """
     default_cfg = default_cfgs['tf_efficientnet_b2']
     kwargs['bn_eps'] = _BN_EPS_TF_DEFAULT
@@ -1499,7 +1499,7 @@ def tf_efficientnet_b2(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def tf_efficientnet_b3(num_classes, in_chans=3, pretrained=False, **kwargs):
+def tf_efficientnet_b3(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ EfficientNet-B3. Tensorflow compatible variant """
     default_cfg = default_cfgs['tf_efficientnet_b3']
     kwargs['bn_eps'] = _BN_EPS_TF_DEFAULT
@@ -1513,7 +1513,7 @@ def tf_efficientnet_b3(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def tf_efficientnet_b4(num_classes, in_chans=3, pretrained=False, **kwargs):
+def tf_efficientnet_b4(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ EfficientNet-B4. Tensorflow compatible variant """
     default_cfg = default_cfgs['tf_efficientnet_b4']
     kwargs['bn_eps'] = _BN_EPS_TF_DEFAULT
@@ -1527,7 +1527,7 @@ def tf_efficientnet_b4(num_classes, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def tf_efficientnet_b5(num_classes, in_chans=3, pretrained=False, **kwargs):
+def tf_efficientnet_b5(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """ EfficientNet-B5. Tensorflow compatible variant """
     default_cfg = default_cfgs['tf_efficientnet_b5']
     kwargs['bn_eps'] = _BN_EPS_TF_DEFAULT
diff --git a/timm/models/gluon_resnet.py b/timm/models/gluon_resnet.py
index a8877bd9..96e61aad 100644
--- a/timm/models/gluon_resnet.py
+++ b/timm/models/gluon_resnet.py
@@ -361,7 +361,7 @@ class GluonResNet(nn.Module):
         return x
 
 
-def gluon_resnet18_v1b(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet18_v1b(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-18 model.
     """
     default_cfg = default_cfgs['gluon_resnet18_v1b']
@@ -372,7 +372,7 @@ def gluon_resnet18_v1b(num_classes=1000, in_chans=3, pretrained=False, **kwargs)
     return model
 
 
-def gluon_resnet34_v1b(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet34_v1b(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-34 model.
     """
     default_cfg = default_cfgs['gluon_resnet34_v1b']
@@ -383,7 +383,7 @@ def gluon_resnet34_v1b(num_classes=1000, in_chans=3, pretrained=False, **kwargs)
     return model
 
 
-def gluon_resnet50_v1b(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet50_v1b(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-50 model.
     """
     default_cfg = default_cfgs['gluon_resnet50_v1b']
@@ -394,7 +394,7 @@ def gluon_resnet50_v1b(num_classes=1000, in_chans=3, pretrained=False, **kwargs)
     return model
 
 
-def gluon_resnet101_v1b(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet101_v1b(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-101 model.
     """
     default_cfg = default_cfgs['gluon_resnet101_v1b']
@@ -405,7 +405,7 @@ def gluon_resnet101_v1b(num_classes=1000, in_chans=3, pretrained=False, **kwargs
     return model
 
 
-def gluon_resnet152_v1b(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet152_v1b(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-152 model.
     """
     default_cfg = default_cfgs['gluon_resnet152_v1b']
@@ -416,7 +416,7 @@ def gluon_resnet152_v1b(num_classes=1000, in_chans=3, pretrained=False, **kwargs
     return model
 
 
-def gluon_resnet50_v1c(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet50_v1c(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-50 model.
     """
     default_cfg = default_cfgs['gluon_resnet50_v1c']
@@ -428,7 +428,7 @@ def gluon_resnet50_v1c(num_classes=1000, in_chans=3, pretrained=False, **kwargs)
     return model
 
 
-def gluon_resnet101_v1c(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet101_v1c(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-101 model.
     """
     default_cfg = default_cfgs['gluon_resnet101_v1c']
@@ -440,7 +440,7 @@ def gluon_resnet101_v1c(num_classes=1000, in_chans=3, pretrained=False, **kwargs
     return model
 
 
-def gluon_resnet152_v1c(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet152_v1c(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-152 model.
     """
     default_cfg = default_cfgs['gluon_resnet152_v1c']
@@ -452,7 +452,7 @@ def gluon_resnet152_v1c(num_classes=1000, in_chans=3, pretrained=False, **kwargs
     return model
 
 
-def gluon_resnet50_v1d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet50_v1d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-50 model.
     """
     default_cfg = default_cfgs['gluon_resnet50_v1d']
@@ -464,7 +464,7 @@ def gluon_resnet50_v1d(num_classes=1000, in_chans=3, pretrained=False, **kwargs)
     return model
 
 
-def gluon_resnet101_v1d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet101_v1d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-101 model.
     """
     default_cfg = default_cfgs['gluon_resnet101_v1d']
@@ -476,7 +476,7 @@ def gluon_resnet101_v1d(num_classes=1000, in_chans=3, pretrained=False, **kwargs
     return model
 
 
-def gluon_resnet152_v1d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet152_v1d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-152 model.
     """
     default_cfg = default_cfgs['gluon_resnet152_v1d']
@@ -488,7 +488,7 @@ def gluon_resnet152_v1d(num_classes=1000, in_chans=3, pretrained=False, **kwargs
     return model
 
 
-def gluon_resnet50_v1e(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet50_v1e(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-50-V1e model. No pretrained weights for any 'e' variants
     """
     default_cfg = default_cfgs['gluon_resnet50_v1e']
@@ -500,7 +500,7 @@ def gluon_resnet50_v1e(num_classes=1000, in_chans=3, pretrained=False, **kwargs)
     return model
 
 
-def gluon_resnet101_v1e(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet101_v1e(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-101 model.
     """
     default_cfg = default_cfgs['gluon_resnet101_v1e']
@@ -512,7 +512,7 @@ def gluon_resnet101_v1e(num_classes=1000, in_chans=3, pretrained=False, **kwargs
     return model
 
 
-def gluon_resnet152_v1e(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet152_v1e(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-152 model.
     """
     default_cfg = default_cfgs['gluon_resnet152_v1e']
@@ -524,7 +524,7 @@ def gluon_resnet152_v1e(num_classes=1000, in_chans=3, pretrained=False, **kwargs
     return model
 
 
-def gluon_resnet50_v1s(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet50_v1s(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-50 model.
     """
     default_cfg = default_cfgs['gluon_resnet50_v1s']
@@ -536,7 +536,7 @@ def gluon_resnet50_v1s(num_classes=1000, in_chans=3, pretrained=False, **kwargs)
     return model
 
 
-def gluon_resnet101_v1s(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet101_v1s(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-101 model.
     """
     default_cfg = default_cfgs['gluon_resnet101_v1s']
@@ -548,7 +548,7 @@ def gluon_resnet101_v1s(num_classes=1000, in_chans=3, pretrained=False, **kwargs
     return model
 
 
-def gluon_resnet152_v1s(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnet152_v1s(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-152 model.
     """
     default_cfg = default_cfgs['gluon_resnet152_v1s']
@@ -560,7 +560,7 @@ def gluon_resnet152_v1s(num_classes=1000, in_chans=3, pretrained=False, **kwargs
     return model
 
 
-def gluon_resnext50_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnext50_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNeXt50-32x4d model.
     """
     default_cfg = default_cfgs['gluon_resnext50_32x4d']
@@ -573,7 +573,7 @@ def gluon_resnext50_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwar
     return model
 
 
-def gluon_resnext101_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnext101_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNeXt-101 model.
     """
     default_cfg = default_cfgs['gluon_resnext101_32x4d']
@@ -586,7 +586,7 @@ def gluon_resnext101_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwa
     return model
 
 
-def gluon_resnext101_64x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnext101_64x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNeXt-101 model.
     """
     default_cfg = default_cfgs['gluon_resnext101_64x4d']
@@ -599,7 +599,7 @@ def gluon_resnext101_64x4d(num_classes=1000, in_chans=3, pretrained=False, **kwa
     return model
 
 
-def gluon_resnext152_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_resnext152_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNeXt152-32x4d model.
     """
     default_cfg = default_cfgs['gluon_resnext152_32x4d']
@@ -612,7 +612,7 @@ def gluon_resnext152_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwa
     return model
 
 
-def gluon_seresnext50_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_seresnext50_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a SEResNeXt50-32x4d model.
     """
     default_cfg = default_cfgs['gluon_seresnext50_32x4d']
@@ -625,7 +625,7 @@ def gluon_seresnext50_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kw
     return model
 
 
-def gluon_seresnext101_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_seresnext101_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a SEResNeXt-101-32x4d model.
     """
     default_cfg = default_cfgs['gluon_seresnext101_32x4d']
@@ -638,7 +638,7 @@ def gluon_seresnext101_32x4d(num_classes=1000, in_chans=3, pretrained=False, **k
     return model
 
 
-def gluon_seresnext101_64x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_seresnext101_64x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a SEResNeXt-101-64x4d model.
     """
     default_cfg = default_cfgs['gluon_seresnext101_64x4d']
@@ -651,7 +651,7 @@ def gluon_seresnext101_64x4d(num_classes=1000, in_chans=3, pretrained=False, **k
     return model
 
 
-def gluon_seresnext152_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_seresnext152_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a SEResNeXt152-32x4d model.
     """
     default_cfg = default_cfgs['gluon_seresnext152_32x4d']
@@ -664,7 +664,7 @@ def gluon_seresnext152_32x4d(num_classes=1000, in_chans=3, pretrained=False, **k
     return model
 
 
-def gluon_senet154(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_senet154(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs an SENet-154 model.
     """
     default_cfg = default_cfgs['gluon_senet154']
diff --git a/timm/models/inception_resnet_v2.py b/timm/models/inception_resnet_v2.py
index 05452b4b..4b884a59 100644
--- a/timm/models/inception_resnet_v2.py
+++ b/timm/models/inception_resnet_v2.py
@@ -318,7 +318,7 @@ class InceptionResnetV2(nn.Module):
         return x
 
 
-def inception_resnet_v2(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def inception_resnet_v2(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     r"""InceptionResnetV2 model architecture from the
     `"InceptionV4, Inception-ResNet..." <https://arxiv.org/abs/1602.07261>`_ paper.
     """
diff --git a/timm/models/inception_v3.py b/timm/models/inception_v3.py
index d9e48ffc..ba9ed493 100644
--- a/timm/models/inception_v3.py
+++ b/timm/models/inception_v3.py
@@ -66,7 +66,7 @@ def _assert_default_kwargs(kwargs):
     assert kwargs.pop('drop_rate', 0.) == 0.
 
 
-def inception_v3(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def inception_v3(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     # original PyTorch weights, ported from Tensorflow but modified
     default_cfg = default_cfgs['inception_v3']
     assert in_chans == 3
@@ -78,7 +78,7 @@ def inception_v3(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def tf_inception_v3(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def tf_inception_v3(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     # my port of Tensorflow SLIM weights (http://download.tensorflow.org/models/inception_v3_2016_08_28.tar.gz)
     default_cfg = default_cfgs['tf_inception_v3']
     assert in_chans == 3
@@ -90,7 +90,7 @@ def tf_inception_v3(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def adv_inception_v3(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def adv_inception_v3(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     # my port of Tensorflow adversarially trained Inception V3 from
     # http://download.tensorflow.org/models/adv_inception_v3_2017_08_18.tar.gz
     default_cfg = default_cfgs['adv_inception_v3']
@@ -103,7 +103,7 @@ def adv_inception_v3(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def gluon_inception_v3(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def gluon_inception_v3(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     # from gluon pretrained models, best performing in terms of accuracy/loss metrics
     # https://gluon-cv.mxnet.io/model_zoo/classification.html
     default_cfg = default_cfgs['gluon_inception_v3']
diff --git a/timm/models/inception_v4.py b/timm/models/inception_v4.py
index 2c47c45a..f25f6515 100644
--- a/timm/models/inception_v4.py
+++ b/timm/models/inception_v4.py
@@ -293,7 +293,7 @@ class InceptionV4(nn.Module):
         return x
 
 
-def inception_v4(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def inception_v4(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['inception_v4']
     model = InceptionV4(num_classes=num_classes, in_chans=in_chans, **kwargs)
     model.default_cfg = default_cfg
diff --git a/timm/models/model_factory.py b/timm/models/model_factory.py
index 7ffb423e..9cce8bd1 100644
--- a/timm/models/model_factory.py
+++ b/timm/models/model_factory.py
@@ -21,7 +21,7 @@ def create_model(
         checkpoint_path='',
         **kwargs):
 
-    margs = dict(num_classes=num_classes, in_chans=in_chans, pretrained=pretrained)
+    margs = dict(pretrained=pretrained, num_classes=num_classes, in_chans=in_chans)
 
     # Not all models have support for batchnorm params passed as args, only gen_efficientnet variants
     supports_bn_params = model_name in gen_efficientnet_model_names()
diff --git a/timm/models/pnasnet.py b/timm/models/pnasnet.py
index 3102e3f8..3f289580 100644
--- a/timm/models/pnasnet.py
+++ b/timm/models/pnasnet.py
@@ -385,13 +385,13 @@ class PNASNet5Large(nn.Module):
         return x
 
 
-def pnasnet5large(num_classes=1000, in_chans=3, pretrained='imagenet'):
+def pnasnet5large(pretrained='imagenet', num_classes=1000, in_chans=3, **kwargs):
     r"""PNASNet-5 model architecture from the
     `"Progressive Neural Architecture Search"
     <https://arxiv.org/abs/1712.00559>`_ paper.
     """
     default_cfg = default_cfgs['pnasnet5large']
-    model = PNASNet5Large(num_classes=1000, in_chans=in_chans)
+    model = PNASNet5Large(num_classes=1000, in_chans=in_chans, **kwargs)
     model.default_cfg = default_cfg
     if pretrained:
         load_pretrained(model, default_cfg, num_classes, in_chans)
diff --git a/timm/models/resnet.py b/timm/models/resnet.py
index 54b9efd3..8f745aca 100644
--- a/timm/models/resnet.py
+++ b/timm/models/resnet.py
@@ -219,7 +219,7 @@ class ResNet(nn.Module):
         return x
 
 
-def resnet18(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def resnet18(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-18 model.
     """
     default_cfg = default_cfgs['resnet18']
@@ -230,7 +230,7 @@ def resnet18(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def resnet34(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def resnet34(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-34 model.
     """
     default_cfg = default_cfgs['resnet34']
@@ -241,7 +241,7 @@ def resnet34(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def resnet50(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def resnet50(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-50 model.
     """
     default_cfg = default_cfgs['resnet50']
@@ -252,7 +252,7 @@ def resnet50(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def resnet101(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def resnet101(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-101 model.
     """
     default_cfg = default_cfgs['resnet101']
@@ -263,7 +263,7 @@ def resnet101(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def resnet152(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def resnet152(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNet-152 model.
     """
     default_cfg = default_cfgs['resnet152']
@@ -274,7 +274,7 @@ def resnet152(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def resnext50_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def resnext50_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNeXt50-32x4d model.
     """
     default_cfg = default_cfgs['resnext50_32x4d']
@@ -287,7 +287,7 @@ def resnext50_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def resnext101_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def resnext101_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNeXt-101 model.
     """
     default_cfg = default_cfgs['resnext101_32x4d']
@@ -300,7 +300,7 @@ def resnext101_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def resnext101_64x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def resnext101_64x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNeXt101-64x4d model.
     """
     default_cfg = default_cfgs['resnext101_32x4d']
@@ -313,7 +313,7 @@ def resnext101_64x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def resnext152_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def resnext152_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     """Constructs a ResNeXt152-32x4d model.
     """
     default_cfg = default_cfgs['resnext152_32x4d']
diff --git a/timm/models/senet.py b/timm/models/senet.py
index 76690c10..31841e7f 100644
--- a/timm/models/senet.py
+++ b/timm/models/senet.py
@@ -400,7 +400,7 @@ class SENet(nn.Module):
         return x
 
 
-def seresnet18(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def seresnet18(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['seresnet18']
     model = SENet(SEResNetBlock, [2, 2, 2, 2], groups=1, reduction=16,
                   inplanes=64, input_3x3=False,
@@ -412,7 +412,7 @@ def seresnet18(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def seresnet34(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def seresnet34(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['seresnet34']
     model = SENet(SEResNetBlock, [3, 4, 6, 3], groups=1, reduction=16,
                   inplanes=64, input_3x3=False,
@@ -424,7 +424,7 @@ def seresnet34(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def seresnet50(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def seresnet50(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['seresnet50']
     model = SENet(SEResNetBottleneck, [3, 4, 6, 3], groups=1, reduction=16,
                   inplanes=64, input_3x3=False,
@@ -436,7 +436,7 @@ def seresnet50(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def seresnet101(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def seresnet101(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['seresnet101']
     model = SENet(SEResNetBottleneck, [3, 4, 23, 3], groups=1, reduction=16,
                   inplanes=64, input_3x3=False,
@@ -448,7 +448,7 @@ def seresnet101(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def seresnet152(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def seresnet152(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['seresnet152']
     model = SENet(SEResNetBottleneck, [3, 8, 36, 3], groups=1, reduction=16,
                   inplanes=64, input_3x3=False,
@@ -460,7 +460,7 @@ def seresnet152(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def senet154(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def senet154(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['senet154']
     model = SENet(SEBottleneck, [3, 8, 36, 3], groups=64, reduction=16,
                   num_classes=num_classes, in_chans=in_chans, **kwargs)
@@ -470,7 +470,7 @@ def senet154(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def seresnext26_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def seresnext26_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['seresnext26_32x4d']
     model = SENet(SEResNeXtBottleneck, [2, 2, 2, 2], groups=32, reduction=16,
                   inplanes=64, input_3x3=False,
@@ -482,7 +482,7 @@ def seresnext26_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def seresnext50_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def seresnext50_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['seresnext50_32x4d']
     model = SENet(SEResNeXtBottleneck, [3, 4, 6, 3], groups=32, reduction=16,
                   inplanes=64, input_3x3=False,
@@ -494,7 +494,7 @@ def seresnext50_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
     return model
 
 
-def seresnext101_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def seresnext101_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['seresnext101_32x4d']
     model = SENet(SEResNeXtBottleneck, [3, 4, 23, 3], groups=32, reduction=16,
                   inplanes=64, input_3x3=False,
diff --git a/timm/models/xception.py b/timm/models/xception.py
index 44094db7..de536408 100644
--- a/timm/models/xception.py
+++ b/timm/models/xception.py
@@ -228,7 +228,7 @@ class Xception(nn.Module):
         return x
 
 
-def xception(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
+def xception(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
     default_cfg = default_cfgs['xception']
     model = Xception(num_classes=num_classes, in_chans=in_chans, **kwargs)
     model.default_cfg = default_cfg