update transform markdown

Author: cezannec

intro-to-pytorch/Part 7 - Loading Image Data (Exercises).ipynb

@@ -42,7 +42,7 @@
     "dataset = datasets.ImageFolder('path/to/data', transform=transform)\n",
     "```\n",
     "\n",
-    "where `'path/to/data'` is the file path to the data directory and `transforms` is a list of processing steps built with the [`transforms`](http://pytorch.org/docs/master/torchvision/transforms.html) module from `torchvision`. ImageFolder expects the files and directories to be constructed like so:\n",
+    "where `'path/to/data'` is the file path to the data directory and `transform` is a list of processing steps built with the [`transforms`](http://pytorch.org/docs/master/torchvision/transforms.html) module from `torchvision`. ImageFolder expects the files and directories to be constructed like so:\n",
     "```\n",
     "root/dog/xxx.png\n",
     "root/dog/xxy.png\n",
@@ -60,7 +60,7 @@
     "When you load in the data with `ImageFolder`, you'll need to define some transforms. For example, the images are different sizes but we'll need them to all be the same size for training. You can either resize them with `transforms.Resize()` or crop with `transforms.CenterCrop()`, `transforms.RandomResizedCrop()`, etc. We'll also need to convert the images to PyTorch tensors with `transforms.ToTensor()`. Typically you'll combine these transforms into a pipeline with `transforms.Compose()`, which accepts a list of transforms and runs them in sequence. It looks something like this to scale, then crop, then convert to a tensor:\n",
     "\n",
     "```python\n",
-    "transforms = transforms.Compose([transforms.Resize(255),\n",
+    "transform = transforms.Compose([transforms.Resize(255),\n",
     "                                 transforms.CenterCrop(224),\n",
     "                                 transforms.ToTensor()])\n",
     "\n",