diff --git a/torchvision/models/mobilenet.py b/torchvision/models/mobilenet.py
index d90b3f8ef14..8be33d71a4e 100644
--- a/torchvision/models/mobilenet.py
+++ b/torchvision/models/mobilenet.py
@@ -1,207 +1 @@
-from torch import nn
-from torch import Tensor
-from .utils import load_state_dict_from_url
-from typing import Callable, Any, Optional, List
-
-
-__all__ = ['MobileNetV2', 'mobilenet_v2']
-
-
-model_urls = {
-    'mobilenet_v2': 'https://download.pytorch.org/models/mobilenet_v2-b0353104.pth',
-}
-
-
-def _make_divisible(v: float, divisor: int, min_value: Optional[int] = None) -> int:
-    """
-    This function is taken from the original tf repo.
-    It ensures that all layers have a channel number that is divisible by 8
-    It can be seen here:
-    https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
-    :param v:
-    :param divisor:
-    :param min_value:
-    :return:
-    """
-    if min_value is None:
-        min_value = divisor
-    new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
-    # Make sure that round down does not go down by more than 10%.
-    if new_v < 0.9 * v:
-        new_v += divisor
-    return new_v
-
-
-class ConvBNReLU(nn.Sequential):
-    def __init__(
-        self,
-        in_planes: int,
-        out_planes: int,
-        kernel_size: int = 3,
-        stride: int = 1,
-        groups: int = 1,
-        norm_layer: Optional[Callable[..., nn.Module]] = None
-    ) -> None:
-        padding = (kernel_size - 1) // 2
-        if norm_layer is None:
-            norm_layer = nn.BatchNorm2d
-        super(ConvBNReLU, self).__init__(
-            nn.Conv2d(in_planes, out_planes, kernel_size, stride, padding, groups=groups, bias=False),
-            norm_layer(out_planes),
-            nn.ReLU6(inplace=True)
-        )
-
-
-class InvertedResidual(nn.Module):
-    def __init__(
-        self,
-        inp: int,
-        oup: int,
-        stride: int,
-        expand_ratio: int,
-        norm_layer: Optional[Callable[..., nn.Module]] = None
-    ) -> None:
-        super(InvertedResidual, self).__init__()
-        self.stride = stride
-        assert stride in [1, 2]
-
-        if norm_layer is None:
-            norm_layer = nn.BatchNorm2d
-
-        hidden_dim = int(round(inp * expand_ratio))
-        self.use_res_connect = self.stride == 1 and inp == oup
-
-        layers: List[nn.Module] = []
-        if expand_ratio != 1:
-            # pw
-            layers.append(ConvBNReLU(inp, hidden_dim, kernel_size=1, norm_layer=norm_layer))
-        layers.extend([
-            # dw
-            ConvBNReLU(hidden_dim, hidden_dim, stride=stride, groups=hidden_dim, norm_layer=norm_layer),
-            # pw-linear
-            nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
-            norm_layer(oup),
-        ])
-        self.conv = nn.Sequential(*layers)
-
-    def forward(self, x: Tensor) -> Tensor:
-        if self.use_res_connect:
-            return x + self.conv(x)
-        else:
-            return self.conv(x)
-
-
-class MobileNetV2(nn.Module):
-    def __init__(
-        self,
-        num_classes: int = 1000,
-        width_mult: float = 1.0,
-        inverted_residual_setting: Optional[List[List[int]]] = None,
-        round_nearest: int = 8,
-        block: Optional[Callable[..., nn.Module]] = None,
-        norm_layer: Optional[Callable[..., nn.Module]] = None
-    ) -> None:
-        """
-        MobileNet V2 main class
-
-        Args:
-            num_classes (int): Number of classes
-            width_mult (float): Width multiplier - adjusts number of channels in each layer by this amount
-            inverted_residual_setting: Network structure
-            round_nearest (int): Round the number of channels in each layer to be a multiple of this number
-            Set to 1 to turn off rounding
-            block: Module specifying inverted residual building block for mobilenet
-            norm_layer: Module specifying the normalization layer to use
-
-        """
-        super(MobileNetV2, self).__init__()
-
-        if block is None:
-            block = InvertedResidual
-
-        if norm_layer is None:
-            norm_layer = nn.BatchNorm2d
-
-        input_channel = 32
-        last_channel = 1280
-
-        if inverted_residual_setting is None:
-            inverted_residual_setting = [
-                # t, c, n, s
-                [1, 16, 1, 1],
-                [6, 24, 2, 2],
-                [6, 32, 3, 2],
-                [6, 64, 4, 2],
-                [6, 96, 3, 1],
-                [6, 160, 3, 2],
-                [6, 320, 1, 1],
-            ]
-
-        # only check the first element, assuming user knows t,c,n,s are required
-        if len(inverted_residual_setting) == 0 or len(inverted_residual_setting[0]) != 4:
-            raise ValueError("inverted_residual_setting should be non-empty "
-                             "or a 4-element list, got {}".format(inverted_residual_setting))
-
-        # building first layer
-        input_channel = _make_divisible(input_channel * width_mult, round_nearest)
-        self.last_channel = _make_divisible(last_channel * max(1.0, width_mult), round_nearest)
-        features: List[nn.Module] = [ConvBNReLU(3, input_channel, stride=2, norm_layer=norm_layer)]
-        # building inverted residual blocks
-        for t, c, n, s in inverted_residual_setting:
-            output_channel = _make_divisible(c * width_mult, round_nearest)
-            for i in range(n):
-                stride = s if i == 0 else 1
-                features.append(block(input_channel, output_channel, stride, expand_ratio=t, norm_layer=norm_layer))
-                input_channel = output_channel
-        # building last several layers
-        features.append(ConvBNReLU(input_channel, self.last_channel, kernel_size=1, norm_layer=norm_layer))
-        # make it nn.Sequential
-        self.features = nn.Sequential(*features)
-
-        # building classifier
-        self.classifier = nn.Sequential(
-            nn.Dropout(0.2),
-            nn.Linear(self.last_channel, num_classes),
-        )
-
-        # weight initialization
-        for m in self.modules():
-            if isinstance(m, nn.Conv2d):
-                nn.init.kaiming_normal_(m.weight, mode='fan_out')
-                if m.bias is not None:
-                    nn.init.zeros_(m.bias)
-            elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
-                nn.init.ones_(m.weight)
-                nn.init.zeros_(m.bias)
-            elif isinstance(m, nn.Linear):
-                nn.init.normal_(m.weight, 0, 0.01)
-                nn.init.zeros_(m.bias)
-
-    def _forward_impl(self, x: Tensor) -> Tensor:
-        # This exists since TorchScript doesn't support inheritance, so the superclass method
-        # (this one) needs to have a name other than `forward` that can be accessed in a subclass
-        x = self.features(x)
-        # Cannot use "squeeze" as batch-size can be 1 => must use reshape with x.shape[0]
-        x = nn.functional.adaptive_avg_pool2d(x, (1, 1)).reshape(x.shape[0], -1)
-        x = self.classifier(x)
-        return x
-
-    def forward(self, x: Tensor) -> Tensor:
-        return self._forward_impl(x)
-
-
-def mobilenet_v2(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> MobileNetV2:
-    """
-    Constructs a MobileNetV2 architecture from
-    `"MobileNetV2: Inverted Residuals and Linear Bottlenecks" <https://arxiv.org/abs/1801.04381>`_.
-
-    Args:
-        pretrained (bool): If True, returns a model pre-trained on ImageNet
-        progress (bool): If True, displays a progress bar of the download to stderr
-    """
-    model = MobileNetV2(**kwargs)
-    if pretrained:
-        state_dict = load_state_dict_from_url(model_urls['mobilenet_v2'],
-                                              progress=progress)
-        model.load_state_dict(state_dict)
-    return model
+from .mobilenetv2 import MobileNetV2, mobilenet_v2
diff --git a/torchvision/models/mobilenetv2.py b/torchvision/models/mobilenetv2.py
new file mode 100644
index 00000000000..990429bacf9
--- /dev/null
+++ b/torchvision/models/mobilenetv2.py
@@ -0,0 +1,214 @@
+from torch import nn
+from torch import Tensor
+from .utils import load_state_dict_from_url
+from typing import Callable, Any, Optional, List
+
+
+__all__ = ['MobileNetV2', 'mobilenet_v2']
+
+
+model_urls = {
+    'mobilenet_v2': 'https://download.pytorch.org/models/mobilenet_v2-b0353104.pth',
+}
+
+
+def _make_divisible(v: float, divisor: int, min_value: Optional[int] = None) -> int:
+    """
+    This function is taken from the original tf repo.
+    It ensures that all layers have a channel number that is divisible by 8
+    It can be seen here:
+    https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
+    :param v:
+    :param divisor:
+    :param min_value:
+    :return:
+    """
+    if min_value is None:
+        min_value = divisor
+    new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
+    # Make sure that round down does not go down by more than 10%.
+    if new_v < 0.9 * v:
+        new_v += divisor
+    return new_v
+
+
+class ConvBNActivation(nn.Sequential):
+    def __init__(
+        self,
+        in_planes: int,
+        out_planes: int,
+        kernel_size: int = 3,
+        stride: int = 1,
+        groups: int = 1,
+        norm_layer: Optional[Callable[..., nn.Module]] = None,
+        activation_layer: Optional[Callable[..., nn.Module]] = None,
+    ) -> None:
+        padding = (kernel_size - 1) // 2
+        if norm_layer is None:
+            norm_layer = nn.BatchNorm2d
+        if activation_layer is None:
+            activation_layer = nn.ReLU6
+        super(ConvBNReLU, self).__init__(
+            nn.Conv2d(in_planes, out_planes, kernel_size, stride, padding, groups=groups, bias=False),
+            norm_layer(out_planes),
+            activation_layer(inplace=True)
+        )
+
+
+# necessary for backwards compatibility
+ConvBNReLU = ConvBNActivation
+
+
+class InvertedResidual(nn.Module):
+    def __init__(
+        self,
+        inp: int,
+        oup: int,
+        stride: int,
+        expand_ratio: int,
+        norm_layer: Optional[Callable[..., nn.Module]] = None
+    ) -> None:
+        super(InvertedResidual, self).__init__()
+        self.stride = stride
+        assert stride in [1, 2]
+
+        if norm_layer is None:
+            norm_layer = nn.BatchNorm2d
+
+        hidden_dim = int(round(inp * expand_ratio))
+        self.use_res_connect = self.stride == 1 and inp == oup
+
+        layers: List[nn.Module] = []
+        if expand_ratio != 1:
+            # pw
+            layers.append(ConvBNReLU(inp, hidden_dim, kernel_size=1, norm_layer=norm_layer))
+        layers.extend([
+            # dw
+            ConvBNReLU(hidden_dim, hidden_dim, stride=stride, groups=hidden_dim, norm_layer=norm_layer),
+            # pw-linear
+            nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
+            norm_layer(oup),
+        ])
+        self.conv = nn.Sequential(*layers)
+
+    def forward(self, x: Tensor) -> Tensor:
+        if self.use_res_connect:
+            return x + self.conv(x)
+        else:
+            return self.conv(x)
+
+
+class MobileNetV2(nn.Module):
+    def __init__(
+        self,
+        num_classes: int = 1000,
+        width_mult: float = 1.0,
+        inverted_residual_setting: Optional[List[List[int]]] = None,
+        round_nearest: int = 8,
+        block: Optional[Callable[..., nn.Module]] = None,
+        norm_layer: Optional[Callable[..., nn.Module]] = None
+    ) -> None:
+        """
+        MobileNet V2 main class
+
+        Args:
+            num_classes (int): Number of classes
+            width_mult (float): Width multiplier - adjusts number of channels in each layer by this amount
+            inverted_residual_setting: Network structure
+            round_nearest (int): Round the number of channels in each layer to be a multiple of this number
+            Set to 1 to turn off rounding
+            block: Module specifying inverted residual building block for mobilenet
+            norm_layer: Module specifying the normalization layer to use
+
+        """
+        super(MobileNetV2, self).__init__()
+
+        if block is None:
+            block = InvertedResidual
+
+        if norm_layer is None:
+            norm_layer = nn.BatchNorm2d
+
+        input_channel = 32
+        last_channel = 1280
+
+        if inverted_residual_setting is None:
+            inverted_residual_setting = [
+                # t, c, n, s
+                [1, 16, 1, 1],
+                [6, 24, 2, 2],
+                [6, 32, 3, 2],
+                [6, 64, 4, 2],
+                [6, 96, 3, 1],
+                [6, 160, 3, 2],
+                [6, 320, 1, 1],
+            ]
+
+        # only check the first element, assuming user knows t,c,n,s are required
+        if len(inverted_residual_setting) == 0 or len(inverted_residual_setting[0]) != 4:
+            raise ValueError("inverted_residual_setting should be non-empty "
+                             "or a 4-element list, got {}".format(inverted_residual_setting))
+
+        # building first layer
+        input_channel = _make_divisible(input_channel * width_mult, round_nearest)
+        self.last_channel = _make_divisible(last_channel * max(1.0, width_mult), round_nearest)
+        features: List[nn.Module] = [ConvBNReLU(3, input_channel, stride=2, norm_layer=norm_layer)]
+        # building inverted residual blocks
+        for t, c, n, s in inverted_residual_setting:
+            output_channel = _make_divisible(c * width_mult, round_nearest)
+            for i in range(n):
+                stride = s if i == 0 else 1
+                features.append(block(input_channel, output_channel, stride, expand_ratio=t, norm_layer=norm_layer))
+                input_channel = output_channel
+        # building last several layers
+        features.append(ConvBNReLU(input_channel, self.last_channel, kernel_size=1, norm_layer=norm_layer))
+        # make it nn.Sequential
+        self.features = nn.Sequential(*features)
+
+        # building classifier
+        self.classifier = nn.Sequential(
+            nn.Dropout(0.2),
+            nn.Linear(self.last_channel, num_classes),
+        )
+
+        # weight initialization
+        for m in self.modules():
+            if isinstance(m, nn.Conv2d):
+                nn.init.kaiming_normal_(m.weight, mode='fan_out')
+                if m.bias is not None:
+                    nn.init.zeros_(m.bias)
+            elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
+                nn.init.ones_(m.weight)
+                nn.init.zeros_(m.bias)
+            elif isinstance(m, nn.Linear):
+                nn.init.normal_(m.weight, 0, 0.01)
+                nn.init.zeros_(m.bias)
+
+    def _forward_impl(self, x: Tensor) -> Tensor:
+        # This exists since TorchScript doesn't support inheritance, so the superclass method
+        # (this one) needs to have a name other than `forward` that can be accessed in a subclass
+        x = self.features(x)
+        # Cannot use "squeeze" as batch-size can be 1 => must use reshape with x.shape[0]
+        x = nn.functional.adaptive_avg_pool2d(x, (1, 1)).reshape(x.shape[0], -1)
+        x = self.classifier(x)
+        return x
+
+    def forward(self, x: Tensor) -> Tensor:
+        return self._forward_impl(x)
+
+
+def mobilenet_v2(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> MobileNetV2:
+    """
+    Constructs a MobileNetV2 architecture from
+    `"MobileNetV2: Inverted Residuals and Linear Bottlenecks" <https://arxiv.org/abs/1801.04381>`_.
+
+    Args:
+        pretrained (bool): If True, returns a model pre-trained on ImageNet
+        progress (bool): If True, displays a progress bar of the download to stderr
+    """
+    model = MobileNetV2(**kwargs)
+    if pretrained:
+        state_dict = load_state_dict_from_url(model_urls['mobilenet_v2'],
+                                              progress=progress)
+        model.load_state_dict(state_dict)
+    return model
diff --git a/torchvision/models/quantization/mobilenet.py b/torchvision/models/quantization/mobilenet.py
index 1d14410f376..8be33d71a4e 100644
--- a/torchvision/models/quantization/mobilenet.py
+++ b/torchvision/models/quantization/mobilenet.py
@@ -1,94 +1 @@
-from torch import nn
-from torchvision.models.utils import load_state_dict_from_url
-from torchvision.models.mobilenet import InvertedResidual, ConvBNReLU, MobileNetV2, model_urls
-from torch.quantization import QuantStub, DeQuantStub, fuse_modules
-from .utils import _replace_relu, quantize_model
-
-
-__all__ = ['QuantizableMobileNetV2', 'mobilenet_v2']
-
-quant_model_urls = {
-    'mobilenet_v2_qnnpack':
-        'https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth'
-}
-
-
-class QuantizableInvertedResidual(InvertedResidual):
-    def __init__(self, *args, **kwargs):
-        super(QuantizableInvertedResidual, self).__init__(*args, **kwargs)
-        self.skip_add = nn.quantized.FloatFunctional()
-
-    def forward(self, x):
-        if self.use_res_connect:
-            return self.skip_add.add(x, self.conv(x))
-        else:
-            return self.conv(x)
-
-    def fuse_model(self):
-        for idx in range(len(self.conv)):
-            if type(self.conv[idx]) == nn.Conv2d:
-                fuse_modules(self.conv, [str(idx), str(idx + 1)], inplace=True)
-
-
-class QuantizableMobileNetV2(MobileNetV2):
-    def __init__(self, *args, **kwargs):
-        """
-        MobileNet V2 main class
-
-        Args:
-           Inherits args from floating point MobileNetV2
-        """
-        super(QuantizableMobileNetV2, self).__init__(*args, **kwargs)
-        self.quant = QuantStub()
-        self.dequant = DeQuantStub()
-
-    def forward(self, x):
-        x = self.quant(x)
-        x = self._forward_impl(x)
-        x = self.dequant(x)
-        return x
-
-    def fuse_model(self):
-        for m in self.modules():
-            if type(m) == ConvBNReLU:
-                fuse_modules(m, ['0', '1', '2'], inplace=True)
-            if type(m) == QuantizableInvertedResidual:
-                m.fuse_model()
-
-
-def mobilenet_v2(pretrained=False, progress=True, quantize=False, **kwargs):
-    """
-    Constructs a MobileNetV2 architecture from
-    `"MobileNetV2: Inverted Residuals and Linear Bottlenecks"
-    <https://arxiv.org/abs/1801.04381>`_.
-
-    Note that quantize = True returns a quantized model with 8 bit
-    weights. Quantized models only support inference and run on CPUs.
-    GPU inference is not yet supported
-
-    Args:
-     pretrained (bool): If True, returns a model pre-trained on ImageNet.
-     progress (bool): If True, displays a progress bar of the download to stderr
-     quantize(bool): If True, returns a quantized model, else returns a float model
-    """
-    model = QuantizableMobileNetV2(block=QuantizableInvertedResidual, **kwargs)
-    _replace_relu(model)
-
-    if quantize:
-        # TODO use pretrained as a string to specify the backend
-        backend = 'qnnpack'
-        quantize_model(model, backend)
-    else:
-        assert pretrained in [True, False]
-
-    if pretrained:
-        if quantize:
-            model_url = quant_model_urls['mobilenet_v2_' + backend]
-        else:
-            model_url = model_urls['mobilenet_v2']
-
-        state_dict = load_state_dict_from_url(model_url,
-                                              progress=progress)
-
-        model.load_state_dict(state_dict)
-    return model
+from .mobilenetv2 import MobileNetV2, mobilenet_v2
diff --git a/torchvision/models/quantization/mobilenetv2.py b/torchvision/models/quantization/mobilenetv2.py
new file mode 100644
index 00000000000..72c522a2e46
--- /dev/null
+++ b/torchvision/models/quantization/mobilenetv2.py
@@ -0,0 +1,94 @@
+from torch import nn
+from torchvision.models.utils import load_state_dict_from_url
+from torchvision.models.mobilenetv2 import InvertedResidual, ConvBNReLU, MobileNetV2, model_urls
+from torch.quantization import QuantStub, DeQuantStub, fuse_modules
+from .utils import _replace_relu, quantize_model
+
+
+__all__ = ['QuantizableMobileNetV2', 'mobilenet_v2']
+
+quant_model_urls = {
+    'mobilenet_v2_qnnpack':
+        'https://download.pytorch.org/models/quantized/mobilenet_v2_qnnpack_37f702c5.pth'
+}
+
+
+class QuantizableInvertedResidual(InvertedResidual):
+    def __init__(self, *args, **kwargs):
+        super(QuantizableInvertedResidual, self).__init__(*args, **kwargs)
+        self.skip_add = nn.quantized.FloatFunctional()
+
+    def forward(self, x):
+        if self.use_res_connect:
+            return self.skip_add.add(x, self.conv(x))
+        else:
+            return self.conv(x)
+
+    def fuse_model(self):
+        for idx in range(len(self.conv)):
+            if type(self.conv[idx]) == nn.Conv2d:
+                fuse_modules(self.conv, [str(idx), str(idx + 1)], inplace=True)
+
+
+class QuantizableMobileNetV2(MobileNetV2):
+    def __init__(self, *args, **kwargs):
+        """
+        MobileNet V2 main class
+
+        Args:
+           Inherits args from floating point MobileNetV2
+        """
+        super(QuantizableMobileNetV2, self).__init__(*args, **kwargs)
+        self.quant = QuantStub()
+        self.dequant = DeQuantStub()
+
+    def forward(self, x):
+        x = self.quant(x)
+        x = self._forward_impl(x)
+        x = self.dequant(x)
+        return x
+
+    def fuse_model(self):
+        for m in self.modules():
+            if type(m) == ConvBNReLU:
+                fuse_modules(m, ['0', '1', '2'], inplace=True)
+            if type(m) == QuantizableInvertedResidual:
+                m.fuse_model()
+
+
+def mobilenet_v2(pretrained=False, progress=True, quantize=False, **kwargs):
+    """
+    Constructs a MobileNetV2 architecture from
+    `"MobileNetV2: Inverted Residuals and Linear Bottlenecks"
+    <https://arxiv.org/abs/1801.04381>`_.
+
+    Note that quantize = True returns a quantized model with 8 bit
+    weights. Quantized models only support inference and run on CPUs.
+    GPU inference is not yet supported
+
+    Args:
+     pretrained (bool): If True, returns a model pre-trained on ImageNet.
+     progress (bool): If True, displays a progress bar of the download to stderr
+     quantize(bool): If True, returns a quantized model, else returns a float model
+    """
+    model = QuantizableMobileNetV2(block=QuantizableInvertedResidual, **kwargs)
+    _replace_relu(model)
+
+    if quantize:
+        # TODO use pretrained as a string to specify the backend
+        backend = 'qnnpack'
+        quantize_model(model, backend)
+    else:
+        assert pretrained in [True, False]
+
+    if pretrained:
+        if quantize:
+            model_url = quant_model_urls['mobilenet_v2_' + backend]
+        else:
+            model_url = model_urls['mobilenet_v2']
+
+        state_dict = load_state_dict_from_url(model_url,
+                                              progress=progress)
+
+        model.load_state_dict(state_dict)
+    return model