Fix typo

Author: EdjeElectronics

README.md

@@ -42,7 +42,7 @@ TensorFlow-GPU allows your PC to use the video card to provide extra processing
 ### 1. Install Anaconda, CUDA, and cuDNN
 Follow [this YouTube video by Mark Jay](https://www.youtube.com/watch?v=RplXYjxgZbw), which shows the process for installing Anaconda, CUDA, and cuDNN. You do not need to actually install TensorFlow as shown in the video, because we will do that later in Step 2. The video is made for TensorFlow-GPU v1.4, so download and install the CUDA and cuDNN versions for the latest TensorFlow version, rather than CUDA v8.0 and cuDNN v6.0 as instructed in the video. The [TensorFlow website](https://www.tensorflow.org/install/gpu) indicates which versions of CUDA and cuDNN are needed for the latest version of TensorFlow. 
 
-If you are using an older version of TensorFlow, make sure you use the CUDA and cuDNN are compatible with the TensorFlow version you are using. [Here](https://www.tensorflow.org/install/source#tested_build_configurations) is a table showing which version of TensorFlow requires which versions of CUDA and cuDNN.
+If you are using an older version of TensorFlow, make sure you use the CUDA and cuDNN versions that are compatible with the TensorFlow version you are using. [Here](https://www.tensorflow.org/install/source#tested_build_configurations) is a table showing which version of TensorFlow requires which versions of CUDA and cuDNN.
 
 Be sure to install [Anaconda](https://www.anaconda.com/distribution/#download-section) as instructed in the video, because the Anaconda virtual environment will be used for the rest of this tutorial. (Note: The current version of Anaconda uses Python 3.7, which is not officially supported by TensorFlow. However, when creating an Anaconda virtual environment during Step 2d of this tutorial, we will tell it to use Python 3.5.)