DOC document all models in README.rst

* add Inception and Densenet;
* document that pretrained VGG is available;
* fix a typo.

README.rst

@@ -249,6 +249,8 @@ architectures:
    ResNet-50, ResNet-101, ResNet-152
 -  `SqueezeNet <https://arxiv.org/abs/1602.07360>`__: SqueezeNet 1.0, and
    SqueezeNet 1.1
+-  `DenseNet <https://arxiv.org/pdf/1608.06993.pdf>`__: DenseNet-128, DenseNet-169, DenseNet-201 and DenseNet-161
+-  `Inception v3 <https://arxiv.org/abs/1512.00567>`__ : Inception v3
 
 You can construct a model with random weights by calling its
 constructor:
@@ -260,9 +262,11 @@ constructor:
     alexnet = models.alexnet()
     vgg16 = models.vgg16()
     squeezenet = models.squeezenet1_0()
+    densenet = models.densenet_161()
+    inception = models.inception_v3()
 
 We provide pre-trained models for the ResNet variants, SqueezeNet 1.0 and 1.1,
-and AlexNet, using the PyTorch `model zoo <http://pytorch.org/docs/model_zoo.html>`__.
+AlexNet, VGG, Inception v3 and DenseNet using the PyTorch `model zoo <http://pytorch.org/docs/model_zoo.html>`__.
 These can be constructed by passing ``pretrained=True``:
 
 .. code:: python
@@ -271,11 +275,14 @@ These can be constructed by passing ``pretrained=True``:
     resnet18 = models.resnet18(pretrained=True)
     alexnet = models.alexnet(pretrained=True)
     squeezenet = models.squeezenet1_0(pretrained=True)
+    vgg16 = models.vgg16(pretrained=True)
+    densenet = models.densenet_161(pretrained=True)
+    inception = models.inception_v3(pretrained=True)
     
 
 All pre-trained models expect input images normalized in the same way, i.e.
 mini-batches of 3-channel RGB images of shape (3 x H x W), where H and W are expected
-to be atleast 224.
+to be at least 224.
 
 The images have to be loaded in to a range of [0, 1] and then
 normalized using `mean=[0.485, 0.456, 0.406]` and `std=[0.229, 0.224, 0.225]`